Papers with Wikipedia
PubHealthTab: A Public Health Table-based Dataset for Evidence-based Fact Checking (2022.findings-naacl)
Copied to clipboard
| Challenge: | Fact-checking is the task of establishing the veracity of factual information, commonly performed manually by journalists. |
| Approach: | They propose a table fact-checking dataset based on real world public health claims and noisy evidence tables from sources similar to those used by fact checkers. |
| Outcome: | The proposed dataset achieves an overall F1 score of 0.73 . |
The FEVER2.0 Shared Task (D19-66)
Copied to clipboard
| Challenge: | Existing deep neural models are becoming more complex and difficult to understand and characterize their behaviour. |
| Approach: | They present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. |
| Outcome: | The proposed task was based on the second Fact Extraction and VERification (FEVER2.0) shared task. |
Fact Checking or Psycholinguistics: How to Distinguish Fake and True Claims? (D19-66)
Copied to clipboard
| Challenge: | Using psycholinguistic features to distinguish lies from true statements is a difficult task and a problem to be solved. |
| Approach: | They compare psycholinguistic text features with fact checking approaches to distinguish lies from true statements using data from a large ongoing study. |
| Outcome: | The proposed methods outperform both fact checking and human baselines but the accuracy is not high. |
Grounding in social media: An approach to building a chit-chat dialogue model (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing open-domain dialogue models fail to capture and utilize external knowledge, leading to repetitive or generic responses to unseen utterances. |
| Approach: | They propose to use social media comments to improve the raw conversation ability of open-domain dialogue systems. |
| Outcome: | The proposed model improves the raw conversation ability of open-domain dialogue systems by mimicking human responses through casual interactions found on social media. |
Chinese Lexical Substitution: Dataset and Method (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks for lexical substitution (LS) are limited and limited in coverage . despite extensive research on Lexical Substitution in various languages, there is limited evidence for LS in Chinese. |
| Approach: | They propose to use human and machine collaboration to construct a Chinese LS dataset . they combine four unsupervised LS methods to generate candidate substitutes . |
| Outcome: | The proposed method outperforms existing benchmarks on the Chinese lexical substitution task. |
Exploiting Summarization Data to Help Text Simplification (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing text simplification datasets are limited to Wikipedia and Newsela, restricting further development of this field. |
| Approach: | They propose an alignment algorithm to extract sentence pairs from summarization datasets and a method to filter suitable pairs. |
| Outcome: | The proposed algorithm can extract sentence pairs from summarization datasets and perform well with real datasets. |
Tabouid: a Wikipedia-based word guessing game (2020.acl-demos)
Copied to clipboard
| Challenge: | Using Wikipedia articles, we generate word-guessing games using a set of NLP and machine-learning techniques. |
| Approach: | They propose a system which uses Wikipedia to generate word-guessing games. |
| Outcome: | The proposed game is based on Tabouid, a word-guessing board game originally published by Parker Brothers in 1989. |
Improving Question Answering with External Knowledge (D19-58)
Copied to clipboard
| Challenge: | ARC-Easy, ARC Challenge, and OpenBookQA use Wikipedia to augment training data . performance degrades when additional instances exhibit higher difficulty than original training data. |
| Approach: | They propose two methods for exploiting external knowledge for QA in science . they enrich the original corpus with relevant text snippets from an open-domain resource . the second method simply increases the amount of training data by appending additional in-domain instances. |
| Outcome: | The proposed methods achieve gains in accuracy of 8.1%, 13.0%, and 12.8% on science QA tasks. |
Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia (2020.emnlp-demos)
Copied to clipboard
Ikuya Yamada, Akari Asai, Jin Sakuma, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji, Yuji Matsumoto
| Challenge: | Existing tools for learning the embeddings of words and entities from Wikipedia are not yet available. |
| Approach: | They propose a Python-based tool for learning Wikipedia embeddings from Wikipedia . they use a Wikipedia dump file as an argument to issue a single command . |
| Outcome: | The proposed tool achieves state-of-the-art results on the KORE entity relatedness dataset and competitive results on benchmark datasets. |
Knowledge Enhanced Contextual Word Representations (D19-1)
Copied to clipboard
Matthew E. Peters, Mark Neumann, Robert Logan, Roy Schwartz, Vidur Joshi, Sameer Singh, Noah A. Smith
| Challenge: | Existing methods to embed knowledge bases into large pre-training models do not contain any explicit grounding to real world entities and are difficult to recover factual knowledge. |
| Approach: | They propose a method to embed multiple knowledge bases (KBs) into large pretrained models with a Knowledge Attention and Recontextualization mechanism. |
| Outcome: | The proposed model improves perplexity, ability to recall facts and word sense disambiguation. |
Wikipedia as a Resource for Text Analysis and Retrieval (P19-4)
Copied to clipboard
| Challenge: | Tutorial examines the role of Wikipedia in tasks related to text analysis and retrieval. |
| Approach: | tutorial examines the role of Wikipedia in tasks related to text analysis and retrieval. |
| Outcome: | This tutorial examines the role of Wikipedia in tasks related to text analysis and retrieval. |
Augmenting Transformers with KNN-Based Composite Memory for Dialog (2021.tacl-1)
Copied to clipboard
| Challenge: | Recent work has focused on learning architectures with large memories capable of storing external knowledge. |
| Approach: | They propose a method to augment generative Transformer neural networks with information fetching modules. |
| Outcome: | The proposed approach improves performance in generative dialog modeling . external knowledge is retrieved from Wikipedia, images, and human-written dialog utterances . |
Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining (D19-61)
Copied to clipboard
| Challenge: | Entities can be used as effective signals to generate less ambiguous semantic representations and align multiple languages. |
| Approach: | They propose a method to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. |
| Outcome: | The proposed method can generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia . it provides reliable alignment on word/entity level and sentence level, and thus can be used for unsupervised cross-linguistic entity linking. |
Reasoning Over Paragraph Effects in Situations (D19-58)
Copied to clipboard
| Challenge: | a key component of reading a passage is the ability to apply knowledge gained from the passage to a new situation. |
| Approach: | They propose a benchmark for reading comprehension targeting Reasoning Over Paragraph Effects in Situations. |
| Outcome: | The proposed model performs slightly better than randomly guessing an answer of the correct type, but is below the human performance of 89.0%. |
Improving Candidate Generation for Low-resource Cross-lingual Entity Linking (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing approaches to cross-lingual entity linking (XEL) do not extend well to low-resource languages with few Wikipedia pages. |
| Approach: | They propose to improve the model by combining Wikipedia references with a list of plausible candidate entities. |
| Outcome: | The proposed method yields 16.9% in Top-30 gold candidate recall compared with state-of-the-art models. |
Advances in Pre-Training Distributed Word Representations (L18-1)
Copied to clipboard
| Challenge: | Pre-trained word representations are a building block of many Natural Language Processing and Machine Learning applications. |
| Approach: | They propose to combine known tricks and a set of publicly available pre-trained word vector representations to train high-quality representations. |
| Outcome: | The proposed models outperform the current state of the art on a number of tasks while maintaining a high training speed to scale to massive amount of data. |
A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Question Answering (QA) is a growing area of research . state-of-the-art QA models struggle on out-of domain documents without fine-tuning . |
| Approach: | They propose a pipeline for validating and training QA data and an interface for human annotation. |
| Outcome: | The proposed pipeline improves QA performance on domain-specific datasets while preserving the accuracy of the model. |
Towards Open-Domain Topic Classification (2022.naacl-demo)
Copied to clipboard
| Challenge: | Existing supervised classification models are insensitive to class names, but are no longer effective in open-domain tasks where the taxonomy is unbounded. |
| Approach: | They propose a topic classification system that accepts user-defined taxonomy in real time . they train a pretrained language model on a new Wikipedia dataset and train it on Wikipedia . |
| Outcome: | The proposed system improves over existing zero-shot models and performs competitively with weakly-supervised models trained on in-domain data. |
SEDTWik: Segmentation-based Event Detection from Tweets Using Wikipedia (N19-3)
Copied to clipboard
| Challenge: | Recent work on event detection from tweets has focused on localized events or breaking news only. |
| Approach: | They propose to split tweets into segments, extract bursty segments, cluster them, summarize them. |
| Outcome: | The proposed system can detect newsworthy events occurring at different locations of the world from a wide range of categories. |
Visualization of the Topic Space of Argument Search Results in args.me (D18-2)
Copied to clipboard
Yamen Ajjour, Henning Wachsmuth, Dora Kiesel, Patrick Riehmann, Fan Fan, Giuliano Castiglia, Rosemary Adejoh, Bernd Fröhlich, Benno Stein
| Challenge: | args.me is the first search engine for controversial topics . it ranks pro and con arguments by their relevance to a topic . |
| Approach: | They propose a visualization interface for result exploration that provides an overview of main aspects in a barycentric coordinate system. |
| Outcome: | The proposed search engine is the first dedicated argument search engine on the web. |
PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)
Copied to clipboard
Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu
| Challenge: | Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction. |
| Approach: | They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise. |
| Outcome: | The proposed framework achieves state-of-the-art on three public datasets. |
Graph Propagation based Data Augmentation for Named Entity Recognition (2023.acl-short)
Copied to clipboard
| Challenge: | Synthetic data suffer from poor diversity, which leads to performance limitations. |
| Approach: | They propose a graph-propagated data augmentation framework for named entity recognition that uses graph propagation to build relationships between labeled data and unlabeled natural texts. |
| Outcome: | The proposed framework improves on a low-resource named entity recognition dataset. |
WikiAsp: A Dataset for Multi-domain Aspect-based Summarization (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing aspects-based summarization models are domain-specific due to large differences in the type of aspects for different domains. |
| Approach: | They propose a large-scale dataset for multi-domain aspect-based summarization using Wikipedia articles from 20 different domains. |
| Outcome: | The proposed model is based on Wikipedia articles from 20 different domains and uses the section titles and boundaries of each article as a proxy for aspect annotation. |
Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Open-domain question answering (QA) models employ a retriever-reader pipeline . however, state-of-the-art readers fail to capture complex relationships between entities . |
| Approach: | They propose a knowledge graph enhanced passage reader that captures entities in questions and retrieved passages. |
| Outcome: | The proposed knowledge graph enhanced passage reader improves on open-domain QA benchmarks by up to 2.2 exact match scores. |
End-to-End Open-Domain Question Answering with BERTserini (N19-4)
Copied to clipboard
| Challenge: | a new open-domain question answering system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles. |
| Approach: | They propose an end-to-end question answering system that integrates BERT with an IR reader. |
| Outcome: | The proposed system improves on a standard benchmark test collection. |
Divisive Language and Propaganda Detection using Multi-head Attention Transformers with Deep Learning BERT-based Language Models for Binary Classification (D19-50)
Copied to clipboard
| Challenge: | a team of researchers used a pre-trained BERT language model to train propaganda . the model was based on a cloze comprehension test to answer a question about influence operations . |
| Approach: | team used a BERT language model that was pre-trained on Wikipedia and BookCorpus . they used cloze comprehension tests to train the model to answer a propaganda question . |
| Outcome: | The proposed model was trained on Wikipedia and BookCorpus to answer propaganda questions . the team used a neural network that was pre-trained on the Wikipedia and bookCorpus corpus . |
Neural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced from Comparable Corpora (N18-4)
Copied to clipboard
| Challenge: | Recent crowdsourcing efforts and workshops on machine translation have resulted in small amounts of parallel texts for building viable machine translation systems for low resource pairs. |
| Approach: | They propose to use an end-to-end Siamese bidirectional recurrent neural network to extract parallel sentences from Wikipedia to improve BLEU scores on both NMT and phrase-based SMT systems. |
| Outcome: | The proposed approach improves BLEU scores on both NMT and phrase-based SMT systems for the low-resource language pairs English–Hindi and English–Tamil when compared to training exclusively on the limited bilingual corpora. |
Representation Learning of Entities and Documents from Knowledge Base Descriptions (C18-1)
Copied to clipboard
| Challenge: | Using documents extracted from Wikipedia, we train a neural network model that learns distributed representations of entities and documents directly from a knowledge base. |
| Approach: | They propose a neural network model that learns distributed representations of entities from a knowledge base. |
| Outcome: | The proposed model performs state-of-the-art on fine-grained entity typing and multiclass text classification tasks. |
Data Contamination: From Memorization to Exploitation (2022.acl-short)
Copied to clipboard
| Challenge: | Pretrained language models are typically trained on web-based datasets that are often "contaminated" with downstream test sets. |
| Approach: | They propose a method to pretrain BERT models on Wikipedia and labeled downstream datasets and fine-tune them on the relevant task. |
| Outcome: | The proposed method compares models on Wikipedia and labeled downstream datasets on two models and three downstream tasks. |
GameQA: Gamified Mobile App Platform for Building Multiple-Domain Question-Answering Datasets (2023.eacl-demo)
Copied to clipboard
Njall Skarphedinsson, Breki Gudmundsson, Steinar Smari, Marta Kristin Larusdottir, Hafsteinn Einarsson, Abuzar Khan, Eric Nyberg, Hrafn Loftsson
| Challenge: | a common problem with question-answering datasets is that they require annotators to source answers from the internet . a crowd-sourcing platform is available for low-resource languages, but it is limited in terms of information available. |
| Approach: | They propose a crowd-sourcing platform to gather multiple-domain QA data for low-resource languages. |
| Outcome: | The proposed platform rivals large QA datasets for high-resource languages in size and answerability. |
mOKB6: A Multilingual Open Knowledge Base Completion Benchmark (2023.acl-short)
Copied to clipboard
| Challenge: | Open knowledge bases (Open KBCs) are constructed from triples of the form, which can be denoted as (s, r, o) by using open information extraction (Open IE) systems. |
| Approach: | They construct a dataset with facts from Wikipedia in six languages . they use open information extraction systems to extract triples from text . |
| Outcome: | The proposed dataset contains facts from Wikipedia in six languages including English . it improves existing Open KB construction pipeline by doing multilingual coreference resolution and keeping only entity-linked triples . |
How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval (2026.findings-acl)
Copied to clipboard
William Gantt Walden, Kathryn Ricci, Miriam Wanner, Zhengping Jiang, Chandler May, Rongkun Zhou, Benjamin Van Durme
| Challenge: | 22% of claims in Wikipedia *lead* sections are unsupported by the article body . 30% of annotated claims in the article *body* are unbacked by their (publicly accessible) sources . |
| Approach: | They analyze Wikipedia's claim support annotations using a large-scale dataset . they find that 22% of Wikipedia claims are unsupported by the article body . |
| Outcome: | The proposed dataset analyzes claims support annotations on biographical Wikipedia articles. |
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for question answering are limited in the availability of labeled data. |
| Approach: | They propose a hierarchical conditional variational autoencoder for generating QA pairs given unstructured texts as contexts while maximizing mutual information between generated QA pair to ensure consistency. |
| Outcome: | The proposed framework achieves impressive performance gains over baseline models on both tasks, using only a fraction of data for training. |
Towards Multi-Modal Text-Image Retrieval to improve Human Reading (2021.naacl-srw)
Copied to clipboard
| Challenge: | In primary school, children's books, as well as in modern language learning apps, multi-modal learning strategies like illustrations of terms and phrases are used to support reading comprehension. |
| Approach: | They propose to use multi-modal transformers to train multi-dimensional models on text-image retrieval to support a user's reading comprehension of arbitrary text. |
| Outcome: | The proposed model performs poorly because of the short and relatively simple textual data that the current models are trained with. |
How Decoding Strategies Affect the Verifiability of Generated Text (2020.findings-emnlp)
Copied to clipboard
Luca Massarelli, Fabio Petroni, Aleksandra Piktus, Myle Ott, Tim Rocktäschel, Vassilis Plachouras, Fabrizio Silvestri, Sebastian Riedel
| Challenge: | Recent advances in pre-trained language models have generated text of an increasingly high quality. |
| Approach: | They propose a decoding strategy that produces less repetitive and more verifiable text. |
| Outcome: | The proposed method produces less repetitive and more verifiable text than previously used decoding strategies. |
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking (2022.naacl-industry)
Copied to clipboard
| Challenge: | Entity linking is the task of recognising mentions of entities in unstructured text documents and linking them to the corresponding entities in a Knowledge Base (KB) the largest public EL dataset is Wikipedia, which covers just 3% of the entities in Wikidata. |
| Approach: | They propose a model which performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass. |
| Outcome: | The proposed model outperforms state-of-the-art methods on standard datasets by an average of 3.7 F1 and can generalise to large-scale knowledge bases such as Wikidata and zero-shot entity linking. |
Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts (2022.aacl-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a longstanding NLP task that consists of identifying an entity in a sentence or document. |
| Approach: | They construct a dataset of seven entity types annotated over 11,382 tweets . they provide a set of language model baselines and analyze the performance of the model . |
| Outcome: | The proposed dataset contains seven entity types annotated over 11,382 tweets . the authors focus on short-term degradation of NER models over time and strategies to fine-tune a language model over different periods . |
Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking (2026.tacl-1)
Copied to clipboard
| Challenge: | Current methods for automated fact-checking rely on relying on other evaluation metrics and closed knowledge sources. |
| Approach: | They propose a method which combines evidence evaluation with verdict-level proxy scoring. |
| Outcome: | The proposed method outperforms existing methods in accuracy and robustness against human ratings and adversarial tests. |
MATSA: Multi-Agent Table Structure Attribution (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Tabular data present unique challenges for attribution due to ambiguities, complex header hierarchies, and the difficulty in interpreting individual table cells without row and column context. |
| Approach: | They propose a task to generate row and column-level attributions supporting LLM-generated answers. |
| Outcome: | The proposed task outperforms baselines on tabCite and improves F1 score. |
Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multitask dense retrieval are not effective due to corpus inconsistency. |
| Approach: | They propose to train individual dense passage retrievers for different open-domain question-answering tasks and aggregate their predictions during test time. |
| Outcome: | The proposed method achieves state-of-the-art performance on 5 benchmark QA datasets, with up to 10% improvement in top-100 accuracy compared to a joint-training multi-task DPR on SQuAD. |
Content-Based Conflict of Interest Detection on Wikipedia (L18-1)
Copied to clipboard
| Challenge: | Conflict-of-Interest (CoI) editing is a problem on Wikipedia that is highly subjective . a key feature of Wiki sites is to allow people from all over the world to add or modify articles anonymously and without consequence. |
| Approach: | They frame CoI detection as a binary classification problem and explore features for it . they find that stylometric features outperform other types of features and give an F-measure of 0.63 . |
| Outcome: | The proposed method outperforms other features and gives an F-measure of 0.63 . the proposed method is not certain that the set of non-CoI articles contains any CoI articles . |
InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions (2023.tacl-1)
Copied to clipboard
Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi
| Challenge: | In information-seeking conversations, a user may ask questions that are under-specified or unanswerable. |
| Approach: | They present a dataset for information-seeking conversations with mixed-initiative interactions . they use Wikipedia to search for answers and provide relevant information . |
| Outcome: | The proposed system significantly underperforms humans in two of the most recent studies. |
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching (2022.tacl-1)
Copied to clipboard
| Challenge: | Current datasets for conversational question answering do not contain topic switches . people often engage in information-seeking conversations to discover new knowledge . |
| Approach: | They propose an open-domain conversational dataset with topic switches based on Wikipedia. |
| Outcome: | The proposed dataset achieves an F1 of 55.8, falling short of human performance by 14.2 points, indicating the difficulty of the dataset. |
Towards Zero-resource Cross-lingual Entity Linking (D19-61)
Copied to clipboard
| Challenge: | XEL is challenging for most languages because of limited availability of requisite resources . simulated environments that use significant resources are not available in truly low-resource languages . |
| Approach: | They propose improvements to entity candidate generation and disambiguation to make better use of the limited resources available in low-resource languages. |
| Outcome: | The proposed model gains 6-20% end-to-end linking accuracy on four low-resource languages. |
Entity Linking in the Job Market Domain (2024.findings-eacl)
Copied to clipboard
| Challenge: | In Natural Language Processing, entity linking (EL) has centered around Wikipedia, but yet remains underexplored for the job market domain. |
| Approach: | They propose to use a bi-encoder and an autoregressive model to link fine-grained span-level skill mentions to a specific taxonomy entry to quantify labor market demands. |
| Outcome: | The proposed model outperforms GENRE in strict evaluation, but performs better in loose evaluation. |
A Seed Corpus of Hindu Temples in India (2020.lrec-1)
Copied to clipboard
| Challenge: | a scientific study of temples can reveal valuable insights into culture and heritage of India. |
| Approach: | They propose a platform that creates temple corpus from web text on temples. |
| Outcome: | The proposed platform improves the curation of temple corpus using classifiers trained on Wikipedia articles on Hindu temples. |
WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages (C18-1)
Copied to clipboard
| Challenge: | Existing methods to enhance Wikipedia's reference section are not effective. |
| Approach: | They propose a two-step approach that leverages the wikilinks present in a scientific Wikipedia target page and recommends highly relevant references to be included in that target page appropriately and automatically borrowed from the reference section of the wikipedia links. |
| Outcome: | The proposed approach achieves a notably good performance on two datasets from Computer Science and Physics. |
The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches for relation classification are focused on the English language and require lots of training data with human annotations. |
| Approach: | They propose a baseline model based on Multilingual BERT and a new multilingual pretraining setup . they propose 'relationship classification' models that use distant supervision . |
| Outcome: | The proposed model significantly improves the baseline model with distant supervision. |
DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions (2021.acl-long)
Copied to clipboard
| Challenge: | Short textual descriptions of entities provide summaries of their key attributes but generating entity descriptions can be challenging since information is scattered across multiple sources with varied content and style. |
| Approach: | They propose to generate an entity summary description from 37K entities from Wikipedia and Fandom, paired with nine evidence documents on average. |
| Outcome: | The proposed task is entity-centric, more abstractive, and covers a wide range of domains. |
Predicting Cross-lingual Trends in Microblogs (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing trend prediction methods only make predictions within a language, but this is not enough to predict cross-lingual trends. |
| Approach: | They propose a method to predict which microblog trends will cross linguistic boundaries to become popular in other languages and when. |
| Outcome: | The proposed model outperforms existing trend prediction methods and LLM-based approaches by 4% in F1-score . |
eMLM: A New Pre-training Objective for Emotion Related Tasks (2021.acl-short)
Copied to clipboard
| Challenge: | Emotion Masked Language Modelling improves the performance of a pretraining language model for emotion detection and sentiment analysis tasks. |
| Approach: | They propose a BERT-based version of Masked Language Modelling that induces emotion into the model. |
| Outcome: | The proposed model improves on emotion detection and sentiment analysis tasks by 1.2% F-1 . the proposed model also shows increased robustness in the test. |
Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai (2024.acl-srw)
Copied to clipboard
| Challenge: | Xue et al., 2024) have demonstrated that large language models can perform at human level across multitudes of tasks and domains. |
| Approach: | They propose a seed-free framework for generating synthetic instruction-tuning data that incorporates fluency, diversity, and cultural context. |
| Outcome: | The proposed framework achieves competitive performance using only 5,000 instructions compared to state-of-the-art Thai LLMs trained on hundreds of thousands of instructions. |
BLINK with Elasticsearch for Efficient Entity Linking in Business Conversations (2022.naacl-industry)
Copied to clipboard
Md Tahmid Rahman Laskar, Cheng Chen, Aliaksandr Martsinovich, Jonathan Johnston, Xue-Yong Fu, Shashi Bhushan Tn, Simon Corston-Oliver
| Challenge: | Existing systems that align textual mentions of entities to knowledge bases are difficult to deploy in production environments. |
| Approach: | They propose a neural entity linking system that connects entities in business phone conversations to their corresponding Wikipedia and Wikidata entries. |
| Outcome: | The proposed system improves inference speed and memory consumption while maintaining high accuracy. |
Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification (2022.aacl-short)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models are extensively trained on massive heterogeneous datasets, known as pre-training datasets. |
| Approach: | They propose to use Domain Adaptive Pre-training and Task-Adaptive pre-training as intermediate steps before the final finetuning task to cover the target domain vocabulary. |
| Outcome: | The proposed approach is computationally efficient, with 78% fewer parameters trained during TAPT. |
CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata (2021.eacl-main)
Copied to clipboard
Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang’, Saeedeh Shekarpour, Johannes Hoffart, Jens Lehmann
| Challenge: | Existing approaches to target end-to-end entity linking over knowledge bases are not efficient. |
| Approach: | They propose a modular approach to target end-to-end entity linking over knowledge bases. |
| Outcome: | The proposed approach outperforms state-of-the-art approaches on two well-known knowledge bases. |
C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References (2022.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to pretrain open-domain question answering systems lack task-specific annotations. |
| Approach: | They propose to pretrain a two-stage open-domain question answering system with strong transfer capabilities by using a dictionary and a large-scale corpus. |
| Outcome: | The proposed approach leads to 2%-10% gains in top-20 accuracy and improves with reader. |
A Document-Level Text Simplification Dataset for Japanese (2024.lrec-main)
Copied to clipboard
| Challenge: | Document-level text simplification tasks combine summarization and intra-sentence simplification. |
| Approach: | They devised a Japanese document-level text simplification dataset based on newspaper articles and Wikipedia. |
| Outcome: | The proposed dataset compared Japanese document-level text simplification models with English models and newspaper articles. |
Claim Check-Worthiness Detection as Positive Unlabelled Learning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a unified approach to claim check-worthiness detection is a critical component of fact checking systems. |
| Approach: | They propose a unified approach which corrects for misinformation by positive unlabelled learning . they propose citation needed detection from Wikipedia and a ranking task which is a critical component of automatic fact checking systems. |
| Outcome: | The proposed method outperforms the state of the art in two of the three tasks studied in English. |
A Unified Encoder-Decoder Framework with Entity Memory (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to index, retrieve, and read documents as evidence suffer from large computational overheads. |
| Approach: | They propose an encoder-decoder framework with an entity memory that stores entity knowledge as latent representations and pre-trained on Wikipedia along with encoder parameters. |
| Outcome: | The proposed framework outperforms memory-based and non-memory encoder-decoder models on various entity-intensive question answering and generation tasks. |
Unsupervised Bitext Mining and Translation via Self-Trained Contextual Embeddings (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing methods to extract parallel sentences from unaligned text yield surprisingly good results. |
| Approach: | They propose an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text using multilingual BERT to create source and target sentence embeddings for nearest-neighbor search and adapt the model via self-training. |
| Outcome: | The proposed method outperforms existing methods and outperformed previous state-of-the-art methods by boosting translation performance by up to 3.5 BLEU on the WMT’14 French-English and WMT'16 German-English tasks. |
Interpretable Entity Representations through Large-Scale Typing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | In traditional methods for natural language processing, entities are embedded in dense vector spaces with pre-trained models. |
| Approach: | They propose an approach to creating entity representations that are human readable and achieve high performance on entity-related tasks out of the box. |
| Outcome: | The proposed representations are vectors whose values correspond to posterior probabilities over fine-grained entity types, indicating the confidence of a typing model’s decision that the entity belongs to the corresponding type. |
Aggregating Crowdsourced and Automatic Judgments to Scale Up a Corpus of Anaphoric Reference for Fiction and Wikipedia Texts (2023.eacl-main)
Copied to clipboard
Juntao Yu, Silviu Paun, Maris Camilleri, Paloma Garcia, Jon Chamberlain, Udo Kruschwitz, Massimo Poesio
| Challenge: | Existing approaches to scale up anaphoric annotation have not overcome these limitations. |
| Approach: | They propose to use a game-with-a-purpose to ‘complete’ markable annotations by using an anaphoric resolver and an aggregation method for anaphorism. |
| Outcome: | The proposed method could be adopted to greatly speed up annotation time in other projects involving games-with-a-purpose. |
Neural Collective Entity Linking (C18-1)
Copied to clipboard
| Challenge: | Entity linking aims to link entity mentions in texts to knowledge bases, but existing methods rely on local contexts to resolve entities independently. |
| Approach: | They propose a neural model for collective entity linking that integrates local contextual features and global coherence information to improve the computation efficiency. |
| Outcome: | The proposed model improves its performance on five publicly available datasets and can be used to train on Wikipedia hyperlinks to avoid overfitting and domain bias. |
Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation (2026.eacl-long)
Copied to clipboard
Thomas F Burns, Letitia Parcalabescu, Stephan Waeldchen, Michael Barlow, Gregor Ziegltrum, Volker Stampa, Bastian Harren, Björn Deiseroth
| Challenge: | Recent studies show that data quality can significantly boost performance and training efficiency for large language models. |
| Approach: | They propose a German-language dataset curation pipeline that combines heuristic and model-based filtering techniques with synthetic data generation. |
| Outcome: | The proposed pipeline can be used to create a large-scale German pre-training dataset using common Crawl web data, fineweb2 and synthetically generated data conditioned on real, organic web data. |
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Knowledge-based open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. |
| Approach: | They propose a benchmark for evaluating multi-source dialogue knowledge selection and response generation using Wikipedia's wizard of Wikipedia. |
| Outcome: | The proposed benchmark is called multi-source Wizard of Wikipedia (Ms.WoW) it contains clean support knowledge, grounded at the utterance level and partitioned into multiple knowledge sources. |
Cross-document Event Coreference Search: Task, Dataset and Modeling (2022.emnlp-main)
Copied to clipboard
| Challenge: | Cross-document Event Coreference resolution is the task of identifying clusters of text mentions that refer to the same event, whether within a single document or across a document collection. |
| Approach: | They propose a cross-document coreference search task that searches for all coreferring mentions for a query event in a large document collection. |
| Outcome: | The proposed model integrates a powerful coreference scoring scheme into the DPR architecture, yielding improved performance. |
Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations (D19-1)
Copied to clipboard
| Challenge: | Prior work on pretrained sentence embeddings and benchmarks focused on the capabilities of stand-alone sentences. |
| Approach: | They propose a test suite of tasks to evaluate whether sentence representations include broader context information. |
| Outcome: | The proposed training objectives help to encode different aspects of information in document structures. |
Zero-shot Fact Verification by Claim Generation (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for fact verification require large datasets, which can be expensive. |
| Approach: | They propose a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. |
| Outcome: | The proposed framework reduces the demand for human-annotated training data and improves a model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. |
Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study (2021.tacl-1)
Copied to clipboard
| Challenge: | Recent advances in open-domain question answering (ODQA) have led to human-level performance on many datasets. |
| Approach: | They provide a comprehensive and quantitative analysis about the difficulty of book QA . they compare the results of their research with extensive ODQA experiments . |
| Outcome: | The proposed model outperforms existing models on event-oriented questions on the NarrativeQA dataset. |
Knowledge-Rich Self-Supervision for Biomedical Entity Linking (2022.findings-emnlp)
Copied to clipboard
Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon
| Challenge: | Entity linking is challenging in high-value domains with myriad entities . standard classification approaches suffer from the annotation bottleneck . |
| Approach: | They propose a self-supervised approach to learn domain knowledge for biomedical entity linking . it generates self-reported mention examples on unlabeled text and trains contextual encoder . |
| Outcome: | The proposed method outperforms existing methods by 20 points in accuracy on biomedical datasets. |
REVerSum: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives (2025.coling-industry)
Copied to clipboard
| Challenge: | Creating new articles and editing older ones is expensive and time-consuming. |
| Approach: | They propose a multi-staged retrieval-augmented generation technique to leverage personal narratives to enhance Wikipedia’s B and C category biography articles. |
| Outcome: | The proposed approach outperforms the best performing baseline by 17% in terms of integrability to the original Wikipedia article and 28.5% in terms informativeness. |
How Large Language Models are Transforming Machine-Paraphrase Plagiarism (2022.emnlp-main)
Copied to clipboard
| Challenge: | Autoregressive paraphrasing tools can be used to generate convincing plagiarized texts with minimal effort. |
| Approach: | They evaluate the detection performance of large autoregressive models for machine-paraphrase generation on scientific articles from arXiv, student theses, and Wikipedia. |
| Outcome: | The proposed models generate paraphrases indistinguishable from original work and human experts rate the quality of generated examples as high as originals. |
A Corpus to Learn Refer-to-as Relations for Nominals (L18-1)
Copied to clipboard
| Challenge: | Existing work on how to learn refer-to-as relations from large unlabeled corpora lacks coreferential information. |
| Approach: | They propose to use Wikipedia to generate coreferential neural embeddings for nominals . they use coreference resolution as a proxy to evaluate the neural embeds for noun phrases . |
| Outcome: | The proposed dataset can be leveraged to construct representations for coreferential nominals from Wikipedia. |
MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages (2023.tacl-1)
Copied to clipboard
Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin
| Challenge: | MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world. |
| Approach: | They have gathered over 726k high-quality relevance judgments for 78k queries over Wikipedia in these languages, where all annotations have been performed by native speakers hired by their team. |
| Outcome: | MIRACL covers languages that are typologically close as well as distant from 10 language families and 13 sub-families, associated with varying amounts of publicly available resources. |
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them (2021.tacl-1)
Copied to clipboard
Patrick Lewis, Yuxiang Wu, Linqing Liu, Pasquale Minervini, Heinrich Küttler, Aleksandra Piktus, Pontus Stenetorp, Sebastian Riedel
| Challenge: | Open-domain Question Answering models that directly leverage question-answer (QA) pairs show promise in terms of speed and memory compared with conventional models which retrieve and read from text corpora. |
| Approach: | They propose a question-answer (QA)-pair retriever to facilitate improved QA-patch models by introducing Probably Asked Questions (PAQ) they propose QA pair retriever, RePAQ, which preempts and caches test questions, enabling it to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. |
| Outcome: | The proposed model outperforms baseline models by 5% but trails RePAQ by 15% . it can be configured for size (under 500MB) or speed (over 1K questions per second) while retaining high accuracy. |
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmented Generation (2025.findings-naacl)
Copied to clipboard
Yiruo Cheng, Kelong Mao, Ziliang Zhao, Guanting Dong, Hongjin Qian, Yongkang Wu, Tetsuya Sakai, Ji-Rong Wen, Zhicheng Dou
| Challenge: | Existing research focuses on single-turn RAG, leaving a gap in addressing multi-turn conversations . a new benchmark is designed to assess RAG systems in realistic multi-turned conversations based on Wikipedia . |
| Approach: | They propose a large-scale benchmark to assess RAG systems in multi-turn contexts . CORAL includes diverse information-seeking conversations automatically derived from Wikipedia . authors propose unified framework to standardize various conversational RAG methods . |
| Outcome: | The proposed framework supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling. |
Knowledge-Guided Paraphrase Identification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for paraphrase identification (PI) are limited due to lack of professional knowledge. |
| Approach: | They propose to leverage Wikipedia knowledge to accurately identify paraphrases by mining outline knowledge of given sentences from Wikipedia. |
| Outcome: | The proposed framework outperforms state-of-the-art models on two public datasets: PARADE and clinicalSTS2019. |
Cross-Lingual Learning-to-Rank with Shared Representations (N18-2)
Copied to clipboard
| Challenge: | Cross-lingual information retrieval (CLIR) is a document retrieval task where the documents are written in a language different from that of the user's query. |
| Approach: | They propose a large-scale dataset derived from Wikipedia to support CLIR research in 25 languages. |
| Outcome: | The proposed model can improve the results of Swahili-English CLIR in Japanese and Japanese. |
Lost and Found: Computational Quality Assurance of Crowdsourced Knowledge on Morphological Defectivity in Wiktionary (2025.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that wikis are not reliable for linguistic knowledge of defects in understudied languages. |
| Approach: | They customize a neural morphological analyzer to annotate Latin and Italian corpora . they validated morphology using crowd-sourced data from Wiktionary to find defects . |
| Outcome: | The proposed algorithm annotates Latin and Italian corpora using crowd-sourced data . results show that 7% of Latin lemmata listed as defective show strong corpus evidence of being non-defective. |
FEVER: a Large-scale Dataset for Fact Extraction and VERification (N18-1)
Copied to clipboard
| Challenge: | 185,445 claims generated by altering sentences from Wikipedia are verified without knowledge of the sentence they were derived from. |
| Approach: | They propose a publicly available dataset for verification against textual sources, FEVER: Fact Extraction and VERification. |
| Outcome: | The proposed dataset achieves 31.87% accuracy on labeling a claim accompanied by the correct evidence, compared to 50.91% if we ignore the evidence. |
Text Segmentation as a Supervised Learning Task (N18-2)
Copied to clipboard
| Challenge: | Existing datasets for text segmentation are small in size and do not represent the natural distribution of text in documents. |
| Approach: | They propose a large dataset for text segmentation that is automatically extracted and labeled from Wikipedia and develop a model based on this dataset. |
| Outcome: | The proposed model generalizes well to unseen natural text. |
A Dataset and Evaluation Framework for Complex Geographical Description Parsing (2020.coling-main)
Copied to clipboard
| Challenge: | Previously, work on toponym resolution has focused on identifying and resolving individual toponyms in text like Adrano, S.Maria di Licodia or Catania. |
| Approach: | They propose a method that parses a set of coordinates and a collection of 360,187 uncurated complex geolocation descriptions to automate the process. |
| Outcome: | The proposed approach automates most of the process by combining Wikipedia and OpenStreetMap. |
Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Nigeria is a multilingual country with 500+ languages. |
| Approach: | They propose to use a pidgin and a creole to analyze the pidgins of Nigeria . they also use machine translation to analyze their results . |
| Outcome: | The results show that the two pidgins do not represent each other and are hard to teach . the results show the pidgin varieties are underrepresented in Generative AI . |
SeNsER: Learning Cross-Building Sensor Metadata Tagger (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Sensor metadata tagging is a key component of smart building applications. |
| Approach: | They propose a framework that learns a sensor metadata tagger for a new building based on its raw metadata and some existing fully annotated building. |
| Outcome: | The proposed framework learns a sensor metadata tagger for a new building based on its raw metadata and some existing fully annotated building. |
Description-Based Zero-shot Fine-Grained Entity Typing (N19-1)
Copied to clipboard
| Challenge: | Existing systems consider a small set of coarse types, but fine-grained Entity Typing can be used for a variety of tasks. |
| Approach: | They propose a zero-shot entity typing approach that utilizes the type description available from Wikipedia to build a distributed semantic representation of the types. |
| Outcome: | The proposed method is able to recognize novel types without additional training on a public benchmark dataset. |
ToTTo: A Controlled Table-To-Text Generation Dataset (2020.emnlp-main)
Copied to clipboard
Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, Dipanjan Das
| Challenge: | Existing methods for data-to-text generation often hallucinate phrases not supported by the Wikipedia table. |
| Approach: | They propose a controlled task where annotators directly revise existing Wikipedia sentences to generate a one-sentence description. |
| Outcome: | The proposed task produces a one-sentence description from a Wikipedia table and highlighted cells. |
Chain-of-Skills: A Configurable Model for Open-Domain Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Using customized retrieval models, model transferability and scalability are limited. |
| Approach: | They propose a modular retrieval model where individual modules correspond to key skills that can be reused across datasets. |
| Outcome: | The proposed model outperforms self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA. |
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning (2022.coling-1)
Copied to clipboard
Revanth Gangi Reddy, Vikas Yadav, Md Arafat Sultan, Martin Franz, Vittorio Castelli, Heng Ji, Avirup Sil
| Challenge: | Existing neural IR systems rely on lexical matching for query-passage alignment, while masked language models use a dual encoder architecture to encode passages and questions into continuous vector representations. |
| Approach: | They propose to enhance the out-of-domain generalization of Dense Passage Retrieval (DPR) through synthetic data augmentation only in the source domain. |
| Outcome: | The proposed model outperforms existing models in in-domain and zero-shot evaluations on Wikipedia-based datasets. |
Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable potential in assisting with mathematical reasoning on different downstream tasks. |
| Approach: | They propose two new tools for autoformalizing real-world mathematical definitions from Wikipedia and arXiv papers. |
| Outcome: | The proposed methods improve definitions by up to 16% and undefined errors by 43%. |
Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent studies have reported that domain mismatch prevents cross-lingual transfer . UBLI and UNMT do not work well when underlying monolingual corpora come from different domains . |
| Approach: | They show that a simple initialization regimen can overcome domain mismatch in cross-lingual transfer . they pre-train word embeddings on concatenated domain-mismatched corpora and use them as initializations . |
| Outcome: | The initialization regimen can overcome the domain mismatch effect in cross-lingual transfer learning . the initializations were used for MUSE UBLI, UN Parallel UNMT, and the SemEval 2017 task . |
Acrostic Poem Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Acrostic poems contain a hidden message; typically, the first letter of each line spells out a word or short phrase. |
| Approach: | They propose a task for acrostic poem generation in English with multiple constraints . they define the task as a generation task with multiple constraint constraints based on a conditional neural language model and a neural rhyming model . |
| Outcome: | The proposed task is based on a baseline model and a neural rhyming model. |
Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale language models (LLMs) like ChatGPT have demonstrated impressive abilities in generating responses based on human instructions. however, their use in the medical domain can be challenging due to their lack of specific, in-depth knowledge. |
| Approach: | They propose a system that integrates authoritative medical textbooks into LLMs’ framework using plug-and-play modules. |
| Outcome: | The proposed system outperforms the specialized Med-PaLM 2 model on three medical QA tasks by 11.6% to 16.6%. |
MuSeCLIR: A Multiple Senses and Cross-lingual Information Retrieval Dataset (2022.coling-1)
Copied to clipboard
| Challenge: | Existing datasets for cross-lingual information retrieval (CLIR) are dominated by searches for named entity mentions, which does not provide a good measure for disambiguation performance. |
| Approach: | They propose a dataset to evaluate CLIR systems' disambiguation ability based on polysemous common nouns with multiple possible translations. |
| Outcome: | The proposed dataset shows that it has a higher requirement on the ability of CLIR systems to disambiguate query terms. |
Low-resource Entity Set Expansion: A Comprehensive Study on User-generated Text (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing benchmarks for entity set expansion (ESE) are limited to well-formed text and well-defined concepts. |
| Approach: | They propose to use user-generated text to assess the generalizability of ESE methods by identifying phenomena such as non-named entities, multifaceted entities and vague concepts. |
| Outcome: | The proposed methods are based on user-generated text to assess their generalizability and performance. |
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata (N18-2)
Copied to clipboard
Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Laforest, Jonathon Hare, Elena Simperl
| Challenge: | Existing Wikipedia content is unevenly distributed among 287 languages . authors propose a neural network architecture that generates textual summaries from Wikidata triples . |
| Approach: | They propose an automated approach to generate Wikipedia summaries from Wikidata triples using structured data. |
| Outcome: | The proposed approach is tested on Arabic and Esperanto languages with limited editors and content in the most under-resourced Wikipedias. |
Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Jiyue Jiang, Alfred Kar Yin Truong, Yanyu Chen, Qinghang Bao, Sheng Wang, Pengan Chen, Jiuming Wang, Lingpeng Kong, Yu Li, Chuan Wu
| Challenge: | Cantonese is considered a low-resource language due to the dominance of Mandarin . rich colloquial vocabulary of Cantone, English loanwords, and code-switching characteristics add to the complexity of corpus collection and processing. |
| Approach: | We collect Cantonese texts from open source corpora, Hong Kong-specific forums, Wikipedia . we refine the model through supervised fine-tuning on curated Cantonesian tasks . |
| Outcome: | The model achieves state-of-the-art (SOTA) performance on four Cantonese benchmarks. |
AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports (2024.lrec-main)
Copied to clipboard
Lukas Lange, Marc Müller, Ghazaleh Haratinezhad Torbati, Dragan Milchevski, Patrick Grau, Subhash Chandra Pujari, Annemarie Friedrich
| Challenge: | Abstract: Natural language processing can help with managing large amounts of unstructured information. |
| Approach: | They propose to annotate a CC-BY-SA-licensed dataset of cyber threat reports . they use named entities, temporal expressions, and cybersecurity-specific concepts . |
| Outcome: | The proposed dataset annotates reports with named entities, temporal expressions, and cybersecurity-specific concepts including implicitly mentioned techniques and tactics. |
Where Have I Heard This Story Before? Identifying Narrative Similarity in Movie Remakes (N18-2)
Copied to clipboard
| Challenge: | Existing methods to identify instances of similar narratives are limited by annotated data. |
| Approach: | They propose a task for identifying instances of similar narratives from a collection of narrative texts. |
| Outcome: | The proposed approach yields an 8% absolute improvement over a baseline on a novel dataset of plot summaries of 577 movie remakes from Wikipedia. |
Learning to Refuse: Towards Mitigating Privacy Risks in LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural languages, but can inadvertently memorize private information, posing significant privacy risks. |
| Approach: | They propose to use a dataset to evaluate machine unlearning methods for protecting personal data in a realistic scenario. |
| Outcome: | The proposed model outperforms baseline methods by 5.65 points and protects target individuals’ personal data while maintaining general capabilities. |
WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia (2021.eacl-main)
Copied to clipboard
| Challenge: | a new approach to extract parallel sentences from Wikipedia articles is proposed . the approach is based on multilingual sentence embeddings, but does not limit it to English . |
| Approach: | They propose to automatically extract parallel sentences from Wikipedia articles in 96 languages . they train neural MT baseline systems on the mined data and evaluate them on the TED corpus . |
| Outcome: | The proposed approach extracts parallel sentences from Wikipedia articles in 96 languages . the extracted sentences achieve strong BLEU scores for many language pairs . |
Domain Regeneration: How well do LLMs match syntactic properties of text domains? (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent improvements in large language models have improved their ability to approximate distributions . authors find that LLMs can suffer from model collapse due to domain considerations based on pretraining . |
| Approach: | They use open source LLMs to regenerate permissively licensed English text from Wikipedia and news text. |
| Outcome: | The proposed model can faithfully match the human-generated distributions in a semantically-controlled setting. |
Guess Me if You Can: Acronym Disambiguation for Enterprises (P18-1)
Copied to clipboard
| Challenge: | Acronyms are abbreviations formed from the initial components of words or phrases . acronyms can be difficult to understand for people who are not familiar with the subject matter . |
| Approach: | They propose a framework to automatically resolve the true meanings of acronyms in a given context . they use the enterprise corpus as input and a high-quality acronym disambiguation system as output . |
| Outcome: | The proposed framework can be deployed to any enterprise to support acronym disambiguation. |
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2021.findings-acl)
Copied to clipboard
Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu Ji, Guihong Cao, Daxin Jiang, Ming Zhou
| Challenge: | Existing methods for injecting knowledge into pre-trained models are inconsistent and can flush out knowledge when multiple kinds of knowledge are injected. |
| Approach: | They propose a framework that retains the original parameters of pre-trained models fixed and supports the development of versatile knowledge-infused models. |
| Outcome: | The proposed framework retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused models. |
Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. |
| Approach: | They propose a bidirectional recurrent neural network based approach to extract parallel sentences from multilingual corpora. |
| Outcome: | The proposed approach outperforms existing approaches on noisy parallel corpora and shows significant improvements in translation performance. |
“Wikily” Supervised Neural Translation Tailored to Cross-Lingual Tasks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation models perform well in low-resource or distant languages. |
| Approach: | They propose a model that leverages Wikipedia for machine translation and cross-lingual tasks without supervision from external parallel data or supervised models in target language. |
| Outcome: | The proposed model outperforms supervised models in Arabic and English translation tasks. |
Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge (2024.eacl-long)
Copied to clipboard
| Challenge: | Using low-resource languages, multilingual language models (ML-LMs) have been developed to transfer factual knowledge across languages. |
| Approach: | They ask how ML-LMs acquire and represent factual knowledge . they use a multilingual factual information probing dataset to investigate ML . |
| Outcome: | The findings highlight the challenge of maintaining consistency factual knowledge across languages. |
Comparing Knowledge Sources for Open-Domain Scientific Claim Verification (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing systems for fact-checking scientific claims assume that the documents containing the evidence are already provided and annotated or contained in a limited corpus. |
| Approach: | They perform an array of experiments to test the performance of open-domain claim verification systems on four datasets of biomedical and health claims in different settings. |
| Outcome: | The proposed system performs better with biomedical and health claims, while Wikipedia is more suited for everyday health concerns. |
Into the Unknown: Generating Geospatial Descriptions for New Environments (2024.findings-acl)
Copied to clipboard
| Challenge: | Similar to vision-and-language navigation tasks, the Rendezvous (RVS) task requires reasoning over allocentric spatial relationships using non-sequential navigation instructions and maps. |
| Approach: | They propose a large-scale augmentation method for generating high-quality synthetic data for new environments using readily available geospatial data. |
| Outcome: | The proposed method improves accuracy on unseen and seen environments by 45.83% on the Rendezvous (RVS) task. |
MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a core task in Natural Language Processing. |
| Approach: | They present a dataset for fine-grained Named Entity Recognition covering 33 entity classes across 12 languages in monolingual and multilingual settings. |
| Outcome: | The proposed dataset covers 33 entity classes across 12 languages in monolingual and multilingual settings. |
“According to . . . ”: Prompting Language Models Improves Quoting from Pre-Training Data (2024.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) may hallucinate and generate false information despite pre-training on factual data. |
| Approach: | They propose a new evaluation metric that measures the extent to which model-produced answers are directly found in underlying text corpora. |
| Outcome: | The proposed evaluation metric measures the extent to which model-produced answers are directly found in underlying text corpora. |
WikiPossessions: Possession Timeline Generation as an Evaluation Benchmark for Machine Reading Comprehension of Long Texts (2020.lrec-1)
Copied to clipboard
| Challenge: | a new corpus of articles is created for the task of temporally-oriented possession . the task is open-domain and can be used to track possession in other texts . |
| Approach: | They propose a new corpus for the task of temporally-oriented possession . they annotate Wikipedia articles for 90 different well-known artifacts . |
| Outcome: | The proposed task is based on annotated Wikipedia articles for 90 artifacts, including paintings, diamonds, and archaeological artifos. |
Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing classification models struggle with large datasets using fine-grained tag sets. |
| Approach: | They propose to structure Wikipedia into a large multi-lingual dataset using an Extended Named Entity tag set. |
| Outcome: | The proposed model fails to describe why Wikipedia articles are used to summarize, translate or answer questions. |
Anonymity at Risk? Assessing Re-Identification Capabilities of Large Language Models in Court Decisions (2024.findings-naacl)
Copied to clipboard
| Challenge: | Despite high re-identification rates on Wikipedia, even the best LLMs struggled with court decisions. |
| Approach: | They construct an anonymized Wikipedia dataset to investigate re-identification risks . they also introduce new metrics to measure performance . |
| Outcome: | The proposed model can be used to identify individuals in court decisions, but it fails in the vast majority of cases. |
InfoSync: Information Synchronization across Multilingual Semi-structured Tables (2023.findings-acl)
Copied to clipboard
| Challenge: | Information Synchronization of semi-structured data across languages is challenging . culture differences, topic preferences, and editing inconsistency lead to information mismatches . |
| Approach: | They propose a method for tabular synchronization that uses information from Wikipedia tables in one language with tables in another language. |
| Outcome: | The proposed method achieves an acceptance rate of 77.28% on Wikipedia . english articles across the web are more timely updated than other languages . |
Robust Lexical Features for Improved Neural Network Named-Entity Recognition (C18-1)
Copied to clipboard
| Challenge: | Named-Entity Recognition (NER) uses word embeddings to extend, rather than replace, hand-crafted features. |
| Approach: | They propose to embed words and entity types into a low-dimensional vector space and compute a feature vector representing each word offline. |
| Outcome: | The proposed representations outperform existing models and achieve state-of-the-art performance. |
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection (2022.emnlp-main)
Copied to clipboard
Suchin Gururangan, Dallas Card, Sarah Dreier, Emily Gade, Leroy Wang, Zeyu Wang, Luke Zettlemoyer, Noah A. Smith
| Challenge: | Language models rely on massive web crawls for diverse text data, but are rife with undesirable content. |
| Approach: | They analyze newspaper articles written by students from across the country to determine whose language is preferred by a quality filter. |
| Outcome: | The results show that newspapers from wealthier, educated, and urban zones are more likely to be classified as high quality. |
Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings (P19-1)
Copied to clipboard
| Challenge: | Existing methods to adapt pretrained embeddings to a large corpus are limited and do not provide sufficient quality. |
| Approach: | They propose to use a small corpus D_T to pretrain embeddings that accurately capture the sense of words in a limited set of focused topics. |
| Outcome: | The proposed embeddings capture the sense of words in a topic in spite of the limited size of the corpus D_T. |
Automatic Construction of a Large-Scale Corpus for Geoparsing Using Wikipedia Hyperlinks (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to evaluate geoparsing systems are small-scale and lack coverage of location expressions on general domains. |
| Approach: | They propose a method to construct a large-scale corpus for geoparsing from Wikipedia articles. |
| Outcome: | The proposed method can annotate multiple location expressions with coordinates even with ambiguous expressions. |
Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution (2021.findings-acl)
Copied to clipboard
| Challenge: | Using unsupervised entity linking, we solve named entity recognition, coreference resolution and relation extraction tasks together. |
| Approach: | They propose to use a knowledge base to inject information into a joint IE model by using unsupervised entity linking. |
| Outcome: | The proposed model improves on two datasets with 5% F1 score. |
Evaluating D-MERIT of Partial-annotation on Information Retrieval (2024.emnlp-main)
Copied to clipboard
Royi Rassin, Yaron Fairstein, Oren Kalinsky, Guy Kushilevitz, Nachshon Cohen, Alexander Libov, Yoav Goldberg
| Challenge: | Using partially-annotated datasets for evaluation can lead to false conclusions . a dataset containing only a subset of relevant passages might result in misleading rankings . |
| Approach: | They propose to use a Wikipedia passage retrieval evaluation set to contain all relevant passages for each query. |
| Outcome: | The proposed dataset can be downloaded from https://d-merit.github.io. |
Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains (2025.findings-naacl)
Copied to clipboard
| Challenge: | a new framework for analyzing hate speech definitions is proposed to address cultural differences in interpretations . a dataset of 493 definitions from more than 100 cultures is used to analyze hate speech . |
| Approach: | They propose a framework for a cross-cultural and cross-domain analysis of hate speech definitions . they use open-source LLMs to analyze the impact of different definitions on hate speech detection . |
| Outcome: | The proposed framework enables cross-cultural and cross-domain analysis of hate speech definitions . it reveals that many domains borrow definitions from one another without taking into account target culture . |
WikiTalkEdit: A Dataset for modeling Editors’ behaviors on Wikipedia (2021.naacl-main)
Copied to clipboard
| Challenge: | Using the WikiTalkEdit dataset, we show how positive emotion and the use of first-person pronouns predict a positive emotional change in a Wikipedia contributor. |
| Approach: | They introduce and analyze WikiTalkEdit, a dataset of conversations and edit histories from Wikipedia, for research in online cooperation and conversation modeling. |
| Outcome: | The proposed dataset supports the classic understanding of style matching, where positive emotion and the use of first-person pronouns predict a positive emotional change in a Wikipedia contributor. |
Harvesting Paragraph-level Question-Answer Pairs from Wikipedia (P18-1)
Copied to clipboard
| Challenge: | Existing models that only take into account sentence-level information do not generate question-answer pairs. |
| Approach: | They propose a neural network approach that incorporates coreference knowledge via a novel gating mechanism for paragraphlevel question generation. |
| Outcome: | The proposed model outperforms existing models on a Wikipedia article question-answer generation task. |
Learning Invariant Representations of Social Media Users (D19-1)
Copied to clipboard
| Challenge: | Existing methods for learning to compare social media users fail to generalize to new users or even to previously known users. |
| Approach: | They propose a procedure to learn a mapping from short episodes of user activity to a vector space in which the distance between points captures the similarity of the corresponding users’ invariant features. |
| Outcome: | The proposed procedure can be applied to users not seen at training time and enables efficient comparisons of users in the resulting vector space. |
The ApposCorpus: a new multilingual, multi-domain dataset for factual appositive generation (2020.coling-main)
Copied to clipboard
| Challenge: | appositives are phrases that appear next to a noun phrase and serve an explicative function. |
| Approach: | They propose a more realistic end-to-end definition of appositive generation with a dataset that spans four languages and two entity types. |
| Outcome: | The proposed model is non-trivial and leaves plenty of room for improvement. |
A Pragmatic Approach for Classical Chinese Word Segmentation (L18-1)
Copied to clipboard
| Challenge: | Classical Chinese word segmentation is largely neglected due to its obsoleteness . a new approach to segmentation using a marked-up corpus is needed . |
| Approach: | They propose a pragmatic approach to deal with Classical Chinese word segmentation without any marked-up corpus. |
| Outcome: | The proposed method makes the CCWS without any marked-up corpus more accurate compared with collocation-based methods. |
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (P19-1)
Copied to clipboard
| Challenge: | a new approach to entity linking relies on unlabeled documents and Wikipedia . a supervised approach uses only natural information, such as unlabed documents . |
| Approach: | They propose a method which exploits only naturally occurring information . they construct a high recall list of candidate entities for each mention in an unlabeled document . |
| Outcome: | The proposed model outperforms fully-supervised state-of-the-art systems on standard test sets. |
Reinforced Sequence Training based Subjective Bias Correction (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for subjective bias correction focus on making one-word edits . a hybrid method to improve the performance of Seq2Seq and transformer-based bias correction models is proposed . |
| Approach: | They propose a reinforced sequence training approach for robust subjective bias correction . it balances bias neutralization with fluency and semantics preservation through reinforcement learning . |
| Outcome: | The proposed method improves subjective bias correction over existing methods . it is cross-trained over multiple sources of bias to be more robust to new styles of biased writing . |
RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models by incorporating external knowledge. |
| Approach: | They propose a method for synthesizing diverse and high-quality RAG instruction data based on any source corpus. |
| Outcome: | The proposed method outperforms existing methods in multiple tasks and achieves strong zero-shot performance. |
Event Linking: Grounding Event Mentions to Wikipedia (2023.eacl-main)
Copied to clipboard
| Challenge: | a new task for natural language understanding is called Event Linking . the context where an event is mentioned lacks the details of this event . |
| Approach: | They propose a new task to link an article's event mention to the most appropriate Wikipedia page . they collect a training set from Wikipedia and evaluate two models to test the task . |
| Outcome: | The proposed model is based on a dataset and a real-world news domain . it is expected that the most appropriate Wikipedia page will provide rich knowledge about the mention . |
WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing datasets for cross-document event coreference resolution are limited and small . authors present a method for identifying clusters of text mentions that refer to the same event . |
| Approach: | They propose a method for generating a large-scale Wikipedia event coreference dataset . they use a generic approach that adapts state-of-the-art models to the cross-document setting . |
| Outcome: | The proposed method outperforms existing models and can be applied to other languages. |
LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in legal NLP have led to a rapid growth of the field . however, many benchmarks are available only in English and no multilingual benchmark exists . |
| Approach: | They propose to use 11 datasets covering 24 languages to compare NLP models. |
| Outcome: | The proposed benchmarks show that even the best baseline only achieves modest results and ChatGPT struggles with many tasks. |
KILT: a Benchmark for Knowledge Intensive Language Tasks (2021.naacl-main)
Copied to clipboard
Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, Vassilis Plachouras, Tim Rocktäschel, Sebastian Riedel
| Challenge: | Existing models for knowledge-intensive language tasks require access to large, external knowledge sources. |
| Approach: | They propose a benchmark for knowledge-intensive language tasks (KILT) they test a shared dense vector index coupled with a seq2seq model to generate disambiguated text. |
| Outcome: | The proposed model outperforms tailor-made approaches on fact checking, open-domain question answering and dialog by generating disambiguated text. |
Using Natural Sentence Prompts for Understanding Biases in Language Models (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work has shown that language models are susceptible to biases present in the training dataset. |
| Approach: | They propose to use natural sentence prompts to analyze gender-occupation biases in language models. |
| Outcome: | The proposed dataset can be used to analyze gender-occupation biases in language models. |
WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a key intermediate task in NLP. |
| Approach: | They propose a method which uses knowledge-based approaches and neural models to produce high-quality training corpora for NER. |
| Outcome: | The proposed method improves on standard benchmarks and yields significant improvements up to 6 span-based F1-score points over previous state-of-the-art systems for data creation. |
External Knowledge-Driven Argument Mining: Leveraging Attention-Enhanced Multi-Network Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Argument mining involves the identification of argument relations (AR) between Argumentative Discourse Units (ADUs). |
| Approach: | They propose to leverage external resources to identify semantic paths linking ADUs . they propose to use WordNet, ConceptNet, and Wikipedia to identify these paths . |
| Outcome: | The proposed architecture achieves F-scores of 0.85, 0.84, 0.70, and 0.87 on four datasets. |
Enhancing Arguments Recognition for Financial Mathematical Reasoning over Hybrid Data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for question answering on textual data are difficult to train and pose a misrecognition problem. |
| Approach: | They propose an approach to train a reasoning program generator to improve argument recognition by aggregating arguments and loss argument set. |
| Outcome: | The proposed method improves the probabilities of proper arguments in a reasoning program generation so that arguments comprising the ground truth have higher weights. |
Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to facilitate natural language understanding rarely involve commonsense or background knowledge. |
| Approach: | They propose a question-answering method that integrates multiple knowledge sources to boost performance. |
| Outcome: | The proposed method outperforms other competing methods on the CommonsenseQA dataset and achieves the new state-of-the-art. |
A Vietnamese Dataset for Evaluating Machine Reading Comprehension (2020.coling-main)
Copied to clipboard
| Challenge: | despite the lack of benchmark datasets for Vietnamese, there are few studies on machine reading comprehension (MRC) . MRC is an essential core for a range of natural language processing applications such as search engines and intelligent agents. |
| Approach: | They propose to use Vietnamese Question Answering Dataset to evaluate machine reading comprehension in Vietnamese . they use over 23,000 human-generated question-answer pairs based on 5,109 Vietnamese articles . |
| Outcome: | The proposed dataset includes over 23,000 human-generated question-answer pairs based on 5,109 passages of 174 Vietnamese articles from Wikipedia. |
WIKIR: A Python Toolkit for Building a Large-scale Wikipedia-based English Information Retrieval Dataset (2020.lrec-1)
Copied to clipboard
| Challenge: | ad-hoc information retrieval methods usually require large amounts of annotated data to be effective. |
| Approach: | They propose an open-source toolkit to automatically build large-scale English information retrieval datasets based on Wikipedia. |
| Outcome: | The proposed toolkit builds large-scale English information retrieval datasets based on Wikipedia with 59,252 queries and 2,617,003 pairs. |
WEXEA: Wikipedia EXhaustive Entity Annotation (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for extracting factual knowledge from text are limited to a few subtasks. |
| Approach: | They propose to use Wikipedia to build a corpus with exhaustive annotations of entity mentions. |
| Outcome: | The proposed system can be used to build supervised datasets and can be reproduced by everyone. |
Extending Multilingual BERT to Low-Resource Languages (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. |
| Approach: | They propose a simple but effective approach to extend multilingual BERT to any new language and show an increase in F1 on M-BERT and new languages. |
| Outcome: | The proposed approach improves on languages already in M-BERT and out of it on other languages. |
C-HTS: A Concept-based Hierarchical Text Segmentation approach (L18-1)
Copied to clipboard
| Challenge: | Existing approaches to hierarchical text segmentation use lexical and/or syntactic similarity to identify the coherent segments of text. |
| Approach: | They propose a Concept-based Hierarchical Text Segmentation approach that uses the semantic relatedness between text constituents to represent meaning. |
| Outcome: | The proposed method performs well on two publicly available datasets. |
OpenEL: An Annotated Corpus for Entity Linking and Discourse in Open Domain Dialogue (2022.lrec-1)
Copied to clipboard
| Challenge: | Named entity recognition (NER), named entity linking and discourse modeling are crucial aspects of natural language understanding for open domain dialogue systems. |
| Approach: | They present an annotated multi-domain corpus for linking entities in open-domain dialogue . they use dialogue context and anaphora resolution to assess the effectiveness of the task . |
| Outcome: | The OpenEL corpus is an annotated multi-domain corpus for linking entities in open-domain dialogue . the system Flair + BLINK has the best performance with a 0.65 F1 score . |
An Analysis of Multilingual FActScore (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in LLMs have demonstrated significant capabilities in many applications. |
| Approach: | They propose a dataset for FActScore on texts generated by strong multilingual LLMs and evaluate their performance in other languages. |
| Outcome: | The proposed dataset shows that LLMs exhibit distinct behaviors in fact extraction and fact scoring tasks. |
Early Discovery of Disappearing Entities in Microblogs (2023.acl-long)
Copied to clipboard
| Challenge: | a study on detecting disappearing entities from noisy microblogs has been published on the real world . a major challenge is detecting uncertain contexts of disappearing entity from noisy posts . |
| Approach: | They propose to use Twitter to detect disappearing entities from noisy microblogs . they build large-scale Twitter datasets of disappearing entity and refine word embeddings based on these data . |
| Outcome: | The proposed method outperforms baseline methods on noisy microblog streams and more than 70% of disappearing entities in Wikipedia are discovered earlier than the update on Wikipedia. |
Few-NERD: A Few-shot Named Entity Recognition Dataset (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to few-shot named entity recognition (NER) focus on coarse-grained entities with few examples, while most unseen entities are fine-grounded. |
| Approach: | They present a human-annotated few-shot named entity recognition dataset . they construct benchmark tasks to assess the generalization capability of models . |
| Outcome: | The proposed model is the first few-shot NER dataset and the largest human-crafted NER data set. |
Possessors Change Over Time: A Case Study with Artworks (D18-1)
Copied to clipboard
| Challenge: | Existing methods to extract possession relations from Wikipedia articles can be used to extract possessors over time. |
| Approach: | They propose to extract possession relations from Wikipedia articles and temporal information indicating when these relations are true. |
| Outcome: | The proposed annotation scheme yields many possessors over time for a given artwork, and an LSTM ensemble can automate the task. |
How to disagree well: Investigating the dispute tactics used on Wikipedia (2022.emnlp-main)
Copied to clipboard
| Challenge: | Disagreements are often studied from the perspective of toxicity or analysing argument structure. |
| Approach: | They propose a dispute tactics framework which unifies both perspectives . they annotate 213 disagreements from Wikipedia Talk pages . |
| Outcome: | The proposed framework can be used to predict disagreements with a transformer-based model. |
Argument Generation with Retrieval, Planning, and Realization (P19-1)
Copied to clipboard
| Challenge: | a novel argument generation framework is used to generate counter-arguments . CANDELA uses a text planning decoder to retrieve arguments of different perspectives . |
| Approach: | They propose a powerful retrieval system and a novel two-step argument generation framework . they use a retrieval-based retrieval platform indexed with 12 million articles from Wikipedia . |
| Outcome: | The proposed framework yields higher BLEU, ROUGE, and METEOR scores than state-of-the-art models. |
Automated Discovery of Mathematical Definitions in Text (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that definition extraction is inefficient for one-sentence definitions . definitions are used in many automatic text analysis tasks, including ontology matching and construction . |
| Approach: | They propose to use convolutional neural network and recurrent neural network to identify mathematical definitions from one sentence. |
| Outcome: | The proposed dataset shows that deep learning methods can identify definitions from mathematical texts. |
Answering questions by learning to rank - Learning to rank by answering questions (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to answer multiple-choice questions with no supporting documents are poor performance. |
| Approach: | They propose a method which can be used to semantically rank documents extracted from Wikipedia . they propose 'semantic ranking' method that latently learns to rank documents by their importance . |
| Outcome: | The proposed model achieves state-of-the-art accuracy on two datasets: ARC Easy and Challenge. |
DialFact: A Benchmark for Fact-Checking in Dialogue (2022.acl-long)
Copied to clipboard
| Challenge: | Existing fact-checking models trained on non-dialogue data fail to perform well on this task. |
| Approach: | They propose a task of fact-checking in dialogue to improve fact- checking performance . they propose to use an annotated conversational claim and Wikipedia snippets as evidence . |
| Outcome: | The proposed task improves fact-checking performance in dialogue. |
OASum: Large-Scale Open Domain Aspect-based Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing generic summarization methods generate only one summary for all different requests which is not optimal for diverse demands. |
| Approach: | They use crowd-sourced knowledge on Wikipedia to create a large-scale open-domain aspect-based summarization dataset with 1 million different aspects on 2 million Wikipedia pages. |
| Outcome: | The proposed model can generate diverse aspect-based summarizations on Wikipedia with zero/few-shot and fine-tuning on seven downstream datasets. |
FRUIT: Faithfully Reflecting Updated Information in Text (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing work on generating edits grounded in external knowledge has focused on correcting grammar and reducing repetitive typing. |
| Approach: | They propose a novel task where the goal is to update an existing article given new evidence by using a dataset of 170K distantly supervised data produced from Wikipedia snapshots. |
| Outcome: | The proposed model can update Wikipedia articles faithfully with new capabilities and opens doors to many new applications. |
Joint Multilingual Supervision for Cross-lingual Entity Linking (D18-1)
Copied to clipboard
| Challenge: | Entity Linking (XEL) systems ground entity mentions written in any language to Wikipedia . XEL is challenging for most languages due to limited availability of resources as supervision . |
| Approach: | They develop a cross-lingual XEL approach that combines supervision from multiple languages jointly. |
| Outcome: | The proposed approach significantly improves on the current state-of-the-art in 8 languages. |
Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on identifying and addressing hallucinations in large language models (LLMs), but the impact of the training process on hallucinosity remains underexplored. |
| Approach: | They propose a training protocol to reduce hallucination variance by dropping embedding indices with significant variability and an unsupervised halluciation detection metric, Efficient EigenScore. |
| Outcome: | The proposed training protocol reduces hallucination variance during training by dropping embedding indices with significant variability. |
Evaluation Dataset and Methodology for Extracting Application-Specific Taxonomies from the Wikipedia Knowledge Graph (2020.lrec-1)
Copied to clipboard
| Challenge: | Recent efforts to extract hierarchical relations from unstructured text have been challenging. |
| Approach: | They propose an iterative method to extract an application-specific gold standard dataset from a Wikipedia knowledge graph and an evaluation framework to assess the quality of noisy automatically extracted taxonomies. |
| Outcome: | The proposed method reduces manual work and provides a first gold standard dataset and evaluation framework. |
Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl (L18-1)
Copied to clipboard
| Challenge: | DepCC is the largest-to-date linguistically analyzed corpus in English . large corpora are essential for the modern data-driven approaches to natural language processing . |
| Approach: | They present a large-to-date linguistically analyzed corpus in English with 365 million documents . they build an index of all sentences and their linguistic meta-data enabling quick search across the corpus . |
| Outcome: | The proposed model outperforms state-of-the-art models on smaller corpora on the SimVerb3500 dataset. |
A Topic-Aligned Multilingual Corpus of Wikipedia Articles for Studying Information Asymmetry in Low Resource Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | a systematic comparison of information coverage in English Wikipedia and Wikipedias in eight other widely spoken languages is needed to bridge the information gap. |
| Approach: | They compare information coverage in English Wikipedia and Wikipedias in eight other widely spoken languages. |
| Outcome: | The analysis quantifies and provides useful insights about the information gap that exists between different language editions of Wikipedia and offers a roadmap for the IR community to bridge this gap. |
KORE 50ˆDYWC: An Evaluation Data Set for Entity Linking Based on DBpedia, YAGO, Wikidata, and Crunchbase (2020.lrec-1)
Copied to clipboard
| Challenge: | A major domain of research in natural language processing is named entity recognition and disambiguation (NERD). |
| Approach: | They extend a widely-used data set to include NERD tasks for DBpedia and YAGO, Wikidata and Crunchbase. |
| Outcome: | The extended data set allows for a broader spectrum of evaluation. |
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for retrieving encyclopedic knowledge lack a large corpus and effective commonsense retriever. |
| Approach: | They propose a framework for retrieval-augmented commonsense reasoning with a large commonsensense corpus and a commonseense retriever. |
| Outcome: | The proposed framework outperforms existing methods on commonsense reasoning tasks. |
Weakly Supervised Multilingual Causality Extraction from Wikipedia (D19-1)
Copied to clipboard
| Challenge: | Existing methods for extracting causality knowledge from Wikipedia are lacking in this area. |
| Approach: | They propose a method for extracting causality knowledge from Wikipedia . they exploit the multilinguality of Wikipedia and the ability to translate to multiple languages . |
| Outcome: | The proposed method achieves precision and recall above 98% and 64%, respectively. |
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings (2021.eacl-main)
Copied to clipboard
| Challenge: | a new method to quantify polysemy is based on basic geometry in the contextual embedding space . word sense annotation has always been one of the tasks with the lowest interannotator agreement . |
| Approach: | They propose a method to estimate polysemy based on simple geometry in contextual embedding space. |
| Outcome: | The proposed method is fully unsupervised and data-driven . it can be used to sample sentences with different senses at no extra cost . |
Know thy Corpus! Robust Methods for Digital Curation of Web corpora (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for estimating the lexicon of Web corpora have not been used to train pre-trained models. |
| Approach: | They propose a framework for digital curation of Web corpora to provide robust estimation of their parameters. |
| Outcome: | The proposed framework provides robust estimation of Web corpora's composition and lexicon . the proposed framework is similar to the BNC and ELMO models, but lacks curated categories . |
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on knowledge editing focus on monolingual scenarios, neglecting the complexities presented by multilingual contexts and multi-hop reasoning. |
| Approach: | They propose a benchmark to evaluate the adaptability of multilingual knowledge editing methods. |
| Outcome: | The proposed benchmark evaluates the adaptability of multilingual knowledge editing methods across five languages. |
WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community (D18-1)
Copied to clipboard
Yiqing Hua, Cristian Danescu-Niculescu-Mizil, Dario Taraborelli, Nithum Thain, Jeffery Sorensen, Lucas Dixon
| Challenge: | Compared to large-scale collections of conversations from social media, Wikipedia talk pages only capture a subset of all discussions and only accounts for the final form of each conversation. |
| Approach: | They propose to reconstruct a corpus that encompasses the complete history of conversations between Wikipedia contributors. |
| Outcome: | The proposed corpus extracts high quality data in both Chinese and English. |
DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | DeAR is an open-source framework that decouples the tasks of LLMs with holistic cross-document analysis. |
| Approach: | They propose an open-source framework that decouples relevance scoring with holistic cross-document analysis. |
| Outcome: | The proposed framework outperforms open-source frameworks in QA and open-domain QA. |
What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context (2020.acl-main)
Copied to clipboard
Ramy Baly, Georgi Karadzhov, Jisun An, Haewoon Kwak, Yoan Dinkov, Ahmed Ali, James Glass, Preslav Nakov
| Challenge: | a growing number of fake news reports are published online, causing a trust crisis . a new study aims to predict political bias and factuality of reporting of entire news outlets . |
| Approach: | They propose to profile entire news outlets and look for those that are likely to publish fake content . they also examine what was written about the target medium and who reads it . |
| Outcome: | The proposed method improves on the current state-of-the-art in analyzing social media and what was written about the target medium. |
HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a dataset for many-hop evidence extraction and fact verification challenges models to reason with information from multiple Wikipedia articles. |
| Approach: | They propose a dataset for many-hop evidence extraction and fact verification . they challenge models to extract facts from Wikipedia articles relevant to a claim . |
| Outcome: | The proposed dataset shows that state-of-the-art models degrade as the number of reasoning hops increases. |
Mining Knowledge for Natural Language Inference from Wikipedia Categories (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Accurate lexical entailment (LE) and natural language inference (NLI) tasks require expensive annotations. |
| Approach: | They propose to pretrain Wikipedia categories for lexical entailment and natural language inference by pretraining them on WikiNLI and transferring them to other knowledge bases. |
| Outcome: | The proposed model can improve strong baselines such as BERT and RoBERTa by pretraining on WikiNLI and transferring the models on downstream tasks. |
Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain-specific pre-trained language models (PLMs) rely on self-supervised learning over large amounts of domain text, without explicitly integrating domain- specific knowledge. |
| Approach: | They propose to integrate domain knowledge from diverse sources into PLMs by using adapters that are pre-trained for individual domain knowledge sources and integrated via an attention-based knowledge controller. |
| Outcome: | The proposed architecture integrates domain knowledge from diverse sources into PLMs in a parameter-efficient way. |
WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types (2022.acl-long)
Copied to clipboard
| Challenge: | Multimodal Entity Linking (MEL) is an essential task for many multimodal applications. |
| Approach: | They propose to use a human-annotated Wikipedia-based multimodal entity linking dataset to improve the quality of existing MEL models. |
| Outcome: | The proposed model uses the visual information of images more effectively than existing models. |
Leveraging LLM For Synchronizing Information Across Multilingual Tables (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent research has sought to improve cross-language synchronization of Wikipedia tables using rule-based methods, but they struggle with complexity and generalization. |
| Approach: | They propose to use a dataset to simulate the process of updating outdated Wikipedia tables and introduce a task decomposition strategy that enhances coherence and accuracy. |
| Outcome: | The proposed model outperforms baselines in Information Updation (1.79%) and Information Addition (20.58%), highlighting its strength in dynamically updating and enriching data across architectures. |
Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | a recent study examines how epistemic markers of certainty, uncertainty, or evidentiality affect LMs' attitudes toward knowledge . accuracies of expressions of high certainty and low certainty are associated with questions . prior work focused on learning the mapping between internal probabilities of a model and an ordinal output . |
| Approach: | They develop a typology of epistemic markers and inject 50 markers into questions . they find that LMs are highly sensitive to epistemical markers in prompts . |
| Outcome: | The proposed model epistemology study shows that LMs are sensitive to epistemic markers in prompts . expressions of high certainty result in 7% decrease in accuracy, while factive verbs hurt performance . |
Massive vs. Curated Embeddings for Low-Resourced Languages: the Case of Yorùbá and Twi (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that word embeddings can be useful for training downstream natural language processing tasks. |
| Approach: | They compare word embeddings obtained by word embeds from curated corpora with a language-dependent processing. |
| Outcome: | The proposed model compares word embeddings with word embeds from curated corpora and a language-dependent processing on two African languages. |
Learning from Child-directed Speech in Two-language Scenarios: A French-English Case-Study (2026.findings-eacl)
Copied to clipboard
| Challenge: | a systematic study of compact language models with limited computational resources is challenging for many research contexts and real-world applications. |
| Approach: | They extend BabyBERTa to English-French scenarios under strictly sizematched data conditions. |
| Outcome: | The proposed model extends to English-French scenarios under sizematched data conditions . the results show context-dependent effects of multilingual training . |
CLIRMatrix: A massively large collection of bilingual and multilingual datasets for Cross-Lingual Information Retrieval (2020.emnlp-main)
Copied to clipboard
| Challenge: | Cross-Lingual Information Retrieval (CLIR) is a retrieval task in which search queries and candidate documents are written in different languages. |
| Approach: | They present a massively large collection of bilingual and multilingual datasets for Cross-Lingual Information Retrieval extracted automatically from Wikipedia. |
| Outcome: | The proposed datasets are the largest and most comprehensive CLIR dataset to date. |
An Open Multilingual System for Scoring Readability of Wikipedia (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on the readability of Wikipedia have focused on English only and there are currently no systems supporting automatic readability assessment of the 300+ languages in Wikipedia. |
| Approach: | They propose a multilingual model to assess Wikipedia's readability using a dataset spanning 14 languages. |
| Outcome: | The proposed model outperforms existing models in a zero-shot scenario and is more accurate than previous benchmarks. |
Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing (D18-1)
Copied to clipboard
| Challenge: | Accurate and complete knowledge bases (KBs) are paramount in NLP. |
| Approach: | They employ multiview learning for increasing the accuracy and coverage of entity type information in KBs by taking high- and low-resource languages from Wikipedia. |
| Outcome: | The proposed learning improves the accuracy and coverage of knowledge bases (KBs) by combining language and representation. |
CINO: A Chinese Minority Pre-trained Language Model (2022.coling-1)
Copied to clipboard
| Challenge: | Existing multilingual pre-trained language models do not perform well on some low-resource languages. |
| Approach: | They propose a multilingual pre-trained language model for Chinese minority languages . they collect documents from Wikipedia and construct two classification datasets . |
| Outcome: | The proposed model outperforms baseline models on various classification tasks. |
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning (2023.acl-long)
Copied to clipboard
Soumya Sanyal, Yichong Xu, Shuohang Wang, Ziyi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren
| Challenge: | Existing methods to improve logical reasoning skills require complex data processing. |
| Approach: | They propose an adaptive pretraining approach to improve logical reasoning over text . they use a subset of Wikipedia sentences for pretraining and a sentence-level classification loss . |
| Outcome: | The proposed model outperforms baselines on LogiQA and ReClor. |
DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion (N19-1)
Copied to clipboard
| Challenge: | Existing datasets for sentence fusion are small and insufficient for training modern neural models. |
| Approach: | They propose a method for automatically-generating fusion examples from raw text . they apply their method to Wikipedia and Sports articles to generate fusion models . |
| Outcome: | The proposed method improves performance on WebSplit when viewed as a sentence fusion task. |
WIKIGENBENCH:Exploring Full-length Wikipedia Generation under Real-World Scenario (2025.coling-main)
Copied to clipboard
Jiebin Zhang, Eugene J. Yu, Qinyu Chen, Chenhao Xiong, Dawei Zhu, Han Qian, Mingbo Song, Weimin Xiong, Xiaoguang Li, Qun Liu, Sujian Li
| Challenge: | Existing efforts to generate Wikipedia articles for new events fall short of real-world application. |
| Approach: | They propose a benchmark to generate Wikipedia articles for new events under real-world scenarios . they use systematic metrics and LLM-based metrics to assess verifiability, organization, and other aspects aligned with real-life scenarios. |
| Outcome: | The proposed benchmarks show that hierarchical-based methods generate more comprehensive content while fine-tuned methods achieve better verifiability. |
Learning to Describe Unknown Phrases with Local and Global Contexts (N19-1)
Copied to clipboard
Shonosuke Ishiwatari, Hiroaki Hayashi, Naoki Yoshinaga, Graham Neubig, Shoetsu Sato, Masashi Toyoda, Masaru Kitsuregawa
| Challenge: | Existing methods for contextual guessing and definition generation do not take clues from local contexts. |
| Approach: | They propose a neural description model that takes clues from local and global contexts . they assume that the target phrase is newly emerged and there is no global context . |
| Outcome: | The proposed model takes clues from local and global contexts over existing methods . it is more effective than existing methods for non-standard English explanation . |
OpenForecast: A Large-Scale Open-Ended Event Forecasting Dataset (2025.coling-main)
Copied to clipboard
| Challenge: | Existing closed-ended event forecasting methods are constrained by a limited answer space. |
| Approach: | They introduce OpenForecast, a large-scale open-ended dataset with three open-ending event forecasting tasks and an automatic LLM-based method for complex events. |
| Outcome: | The proposed method can be used to evaluate the ability of complex event forecasting of large language models. |
ViHateT5: Enhancing Hate Speech Detection in Vietnamese With a Unified Text-to-Text Transformer Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for HSD in Vietnamese focus on fine-tuning general pre-trained models, primarily trained on formal textual datasets like Wikipedia. |
| Approach: | They propose a T5-based HSD model pre-trained on a domain-specific dataset . their results highlight the significance of label distribution in pre-training data on model efficacy. |
| Outcome: | The proposed model can tackle multiple tasks using a unified model and achieve state-of-the-art performance across all standard HSD benchmarks in Vietnamese. |
TWAG: A Topic-Guided Wikipedia Abstract Generator (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models view Wikipedia abstract as plain text, ignoring that it is a description of a certain entity and can be decomposed into different topics. |
| Approach: | They propose a model that guides Wikipedia abstract generation with topical information. |
| Outcome: | The proposed model outperforms baselines and is capable of generating comprehensive abstracts. |
Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Currently, only 20% of the English comments explicitly mention content moderation policies, but as few as 2% of the German and Turkish comments. |
| Approach: | They propose to use a multilingual dataset to predict stances with existing content moderation policies and to use them to explain moderation decisions. |
| Outcome: | The proposed model predicts stances and corresponding reasons with high accuracy, adding transparency to the decision-making process. |
Employing Argumentation Knowledge Graphs for Neural Argument Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating arguments use end-to-end knowledge graphs or are controlled with respect to the argument's topic, aspects, or stance. |
| Approach: | They construct and populate three knowledge graphs and encode them into debate portals and relevant paragraphs from Wikipedia. |
| Outcome: | The proposed model produces arguments with superior quality than those generated without knowledge. |
CSSWiki: A Chinese Sentence Simplification Dataset with Linguistic and Content Operations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets for sentence simplification focus on English, but limited in Chinese . SS tasks are aimed at improving readability and making sentences more accessible for readers . |
| Approach: | They propose an open-source dataset for Chinese sentence simplification based on Wikipedia . they analyze differences in annotation scheme and data statistics between datasets . |
| Outcome: | The proposed dataset contains 1.6k source sentences paired with their simplified versions. |
Evaluating EcoLexiCAT: a Terminology-Enhanced CAT Tool (L18-1)
Copied to clipboard
| Challenge: | EcoLexiCAT is a web-based tool for terminology-enhanced translation of environmental texts . most terminological modules in CAT tools do not go beyond a simple glossary of source and target terms . |
| Approach: | They propose to integrate terminology-enhanced translation into a web-based tool . EcoLexiCAT is a terminology-enriched CAT tool for the English-Spanish-English translation . |
| Outcome: | The EcoLexiCAT tool is an open-source version of the CAT tool MateCat . it enriches a source text with information from a multimodal and multilingual terminological knowledge base on the environment . |
BioMegatron: Larger Biomedical Domain Language Model (2020.emnlp-main)
Copied to clipboard
Hoo-Chang Shin, Yang Zhang, Evelina Bakhturina, Raul Puri, Mostofa Patwary, Mohammad Shoeybi, Raghav Mani
| Challenge: | Existing studies on domain language models do not study the factors affecting performance on domain languages. |
| Approach: | They empirically evaluate factors that can affect performance on domain language applications . sub-word vocabulary set, model size, pre-training corpus, and domain transfer are important . |
| Outcome: | The results show language models trained on biomedical text perform better on biomedicine benchmarks than those trained on general domain text corpora. |
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications . despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. |
| Approach: | They propose a framework for creating a high-quality dataset for multimodal multihop question answering . they use a 5-stage pipeline to acquire relevant multimodal documents from Wikipedia . |
| Outcome: | The proposed framework outperforms existing methods on multimodal multihop question answering datasets. |
Leveraging Wikipedia article evolution for promotional tone detection (2022.acl-long)
Copied to clipboard
| Challenge: | Detecting biased language is useful for a variety of applications, authors say . a dataset for document-level promotional tone detection is available for WikiEvolve . |
| Approach: | They propose a dataset for document-level promotional tone detection using Wikipedia . they use a gradient reversal framework to encode two versions simultaneously . |
| Outcome: | The proposed dataset improves on in-domain and out-of-domain evaluations. |
Summary Cloze: A New Task for Content Selection in Topic-Focused Summarization (D19-1)
Copied to clipboard
| Challenge: | Recent work on topic-focused summarization has focused on generic summarizing due to the size of the available datasets. |
| Approach: | They propose a method to study content selection in topic-focused summarization by narrowing the scope to a sentence-level task. |
| Outcome: | The proposed method can generate a large-scale summary cloze dataset from Wikipedia. |
BioReader: a Retrieval-Enhanced Text-to-Text Transformer for Biomedical Literature (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has equipped language models with the ability to attend over relevant and factual information from non-parametric external sources, drawing a complementary path to architectural scaling. |
| Approach: | They propose a retrieval-enhanced text-to-text model that augments the input prompt by fetching and assembling relevant scientific literature chunks from a neural database centered on PubMed. |
| Outcome: | The proposed model outperforms state-of-the-art models on a broad array of downstream tasks while using up to 3x fewer parameters. |
ClinIDMap: Towards a Clinical IDs Mapping for Data Interoperability (2022.lrec-1)
Copied to clipboard
| Challenge: | a tool for mapping identifiers between clinical ontologies and lexical resources is available. |
| Approach: | They propose a tool for mapping identifiers between clinical ontologies and lexical resources. |
| Outcome: | The proposed mapping tool can be used to enrich existing annotated corpora in multiple languages. |
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing open-domain question answering methods rely on the retriever to gather all evidence in isolation, but our approach uses an intermediary module to perform a chain of reasoning over the retrieved set. |
| Approach: | They propose a new open-domain question answering framework that integrates an intermediary module into the current retriever-reader pipeline and integrates it into the model. |
| Outcome: | The proposed framework outperforms the state-of-the-art on two OTT-QA datasets with an exact match score of 47.3 (45% relative gain). |
Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations (2023.acl-long)
Copied to clipboard
| Challenge: | Named entity recognition models rely on domain-specific dictionaries provided by experts . however, such dictionary sets are infeasible in many domains where they do not exist . |
| Approach: | They propose a framework that generates NER datasets with high-coverage pseudo-dictionaries . phrase retrieval models are used to retrieve popular entities rather than rare ones . |
| Outcome: | The proposed framework outperforms the previous best model by an average F1 score of 4.7 across five NER benchmark datasets. |
TRANSLIT: A Large-scale Name Transliteration Resource (2020.lrec-1)
Copied to clipboard
| Challenge: | Transliteration is the process of expressing a proper name from a source language in the characters of a target language. |
| Approach: | They present a large-scale corpus of transliterated names in 180 languages . they use machine learning to train automatic transliteration . |
| Outcome: | The proposed system achieves 92% accuracy on identification of transliterated pairs. |
Hi-GEC: Hindi Grammar Error Correction in Low Resource Scenario (2025.coling-main)
Copied to clipboard
| Challenge: | Automated Grammatical Error Correction (GEC) is a scarcely explored low-resource language . a recent study focused on English, but it focused on Hindi, which presents unique challenges due to its complex syntax and intricate morphology. |
| Approach: | They propose to use a human-edited dataset to generate Hindi GEC data . they also investigate round trip translation using diverse languages for the technique . |
| Outcome: | The proposed method outperforms other methods in Hindi, showing that it is highly efficient. |
Semantic Relatedness of Wikipedia Concepts – Benchmark Data and a Working Solution (L18-1)
Copied to clipboard
| Challenge: | Existing methods to measure relatedness between Wikipedia concepts are lacking. |
| Approach: | They propose a new type of concept relatedness dataset, WORD, which is annotated by a human . they use this dataset to assess relatedness between Wikipedia concepts using supervised methods. |
| Outcome: | The proposed dataset outperforms existing methods for measuring relatedness between Wikipedia concepts. |
LongForm: Effective Instruction Tuning with Reverse Instructions (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on instruction tuning relies on expensive human annotation and crowd-sourced datasets with alignment issues. |
| Approach: | They propose a method to generate instructions via LLMs from human-written corpus examples using reverse instructions. |
| Outcome: | The proposed method outperforms larger language models without instruction tuning on tasks such as story/recipe generation and long-form question answering. |
TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models (2022.emnlp-main)
Copied to clipboard
Joel Jang, Seonghyeon Ye, Changho Lee, Sohee Yang, Joongbo Shin, Janghoon Han, Gyeonghun Kim, Minjoon Seo
| Challenge: | Language Models (LMs) become outdated as the world changes, a phenomenon called temporal misalignment. |
| Approach: | They propose a lifelong benchmark that utilizes the difference between consecutive snapshots of English Wikipedia and English Wikidata for training and evaluation. |
| Outcome: | The proposed benchmark can be trained on the difference between consecutive snapshots of English Wikipedia and English Wikidata for training and evaluation. |
The Language of Legal and Illegal Activity on the Darknet (P19-1)
Copied to clipboard
| Challenge: | a study of the characteristics of text in the Darknet shows that it has legal and illegal content. |
| Approach: | They compare texts for selling legal and illegal drugs to a control condition . they find several distinguishing features between legal and illicit texts . |
| Outcome: | The authors compare legal and illegal texts to a clear net website with similar content as a control condition. |
BioGen: Generating Biography Summary under Table Guidance on Wikipedia (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for summarizing text have not captured the salient information from an article. |
| Approach: | They propose a table-guided abstractive biography summarization that utilizes factual tables to capture important information and generate a summary of a biography. |
| Outcome: | The proposed method is the first large-scale biography summarization dataset with tables. |
WebIE: Faithful and Robust Information Extraction on the Web (2023.acl-long)
Copied to clipboard
| Challenge: | Existing closed IE datasets are built using Wikipedia, but they have limitations when applied to web domains. |
| Approach: | They propose to annotate 25K triples from WebIE through crowdsourcing and introduce mWebIE, a translation of the annotated set in four other languages. |
| Outcome: | The proposed model trains on 1.6M sentences from the English Common Crawl corpus and includes negative examples to better reflect the data on the web. |
Open-World Evaluation for Retrieving Diverse Perspectives (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing retrieval systems only cover diverse perspectives on 33.74% of the examples . existing systems only focus on relevance to the question, ignoring diversity. |
| Approach: | They build a Benchmark for Retrieval Diversity for Subjective questions (BERDS) based on a question and diverse perspectives associated with the question . they evaluate retrievers paired with a corpus to determine whether each document contains a perspective . |
| Outcome: | The proposed approach improves retrieval diversity on complex questions . existing retrieval systems only cover diverse perspectives on 33.74% of the examples . |
Incorporating medical knowledge in BERT for clinical relation extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are used for diverse NLP tasks such as Information Extraction, Sentiment Analysis and Question/Answering. |
| Approach: | They propose to add medical knowledge to pre-trained language models to facilitate clinical relation extraction using a large text corpus. |
| Outcome: | The proposed model outperforms the state-of-the-art systems on the benchmark i2b2/VA 2010 clinical relation extraction dataset. |
Machine Translation With Weakly Paired Documents (D19-1)
Copied to clipboard
| Challenge: | Recent studies explore the possibility of unsupervised machine translation with monolingual data only. |
| Approach: | They propose a method to mine bilingual sentences from weakly paired documents . they use word distribution-level alignments to constrain word distributions of two weakly-paired documents. |
| Outcome: | The proposed method outperforms previous results on six translation tasks using weakly paired bilingual documents and a large number of bilingual sentences. |
On Reference (In-)Determinacy in Natural Language Inference (2025.findings-naacl)
Copied to clipboard
Sihao Chen, Chaitanya Malaviya, Alex Fabrikant, Hagai Taitelbaum, Tal Schuster, Senaka Buthpitiya, Dan Roth
| Challenge: | Using reference determinacy, models fail to recognize context mismatch in NLI examples . |
| Approach: | They propose a benchmark to identify reference ambiguity in NLI examples . they propose RD as a possible assumption for natural language inference . |
| Outcome: | The proposed benchmark identifies reference ambiguity in natural language inference examples . 80% false contradiction and >50% entailment predictions are found . |
KEPLET: Knowledge-Enhanced Pretrained Language Model with Topic Entity Awareness (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have shown their superiority by pre-training on unstructured text corpus and then fine-tuning on downstream tasks. |
| Approach: | They propose a Knowledge-Enhanced Pre-trained LanguagE model with Topic entity awareness that incorporates the interactions between tokens and mentioned entities in pre-training. |
| Outcome: | The proposed model incorporates the interactions between tokens and mentioned entities in pre-training and is more effective on entity-centric tasks. |
HeGeL: A Novel Dataset for Geo-Location from Hebrew Text (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets in English for textual geolocation are limited because of the location of the place is implicit. |
| Approach: | They propose to use a Hebrew place description corpus to analyze lingual geospatial reasoning. |
| Outcome: | The Hebrew Geo-Location corpus collects literal Hebrew place descriptions and analyzes lingual geospatial reasoning. |
ComplexTempQA: A 100m Dataset for Complex Temporal Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets that focus on temporal knowledge are limited in size and lack comprehensive coverage of temporal information. |
| Approach: | They introduce a large-scale temporal question-answer-matching dataset . the new taxonomy categorizes questions as attributes, comparisons, and counting questions . |
| Outcome: | The proposed dataset surpasses existing benchmarks in scale and scope. |
WiCE: Real-World Entailment for Claims in Wikipedia (2023.emnlp-main)
Copied to clipboard
| Challenge: | Textual entailment models are increasingly used in fact-checking, presupposition verification in question answering, or summary evaluation. |
| Approach: | They propose a new fine-grained textual entailment dataset built on natural claim and evidence pairs extracted from Wikipedia that provides en-tailment judgments over sub-sentence units of the claim and a minimal subset of evidence sentences that support each subclaim. |
| Outcome: | The proposed dataset improves on multiple datasets at test time and shows that real claims involve verification and retrieval problems that existing models fail to address. |
A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification (L18-1)
Copied to clipboard
| Challenge: | Xu et al., 2016) show that a simple neural architecture can be efficiently used for in-domain and cross-domain text simplification. |
| Approach: | They evaluate neural sequence-to-sequence models for text simplification on Wikipedia and Newsela datasets. |
| Outcome: | The proposed model can generalize across corpora and overcome challenges when tested on Wikipedia and Newsela datasets. |
Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing text-to-image models fail to produce appropriate images for cultural concepts or objects not well known or underrepresented in western cultures, such as 'hangari' (a Korean utensil). |
| Approach: | They propose a method which iteratively refines the prompt to improve the alignment between the generated images and underrepresented cultural nouns in text-to-image models. |
| Outcome: | The proposed approach improves the alignment between the generated images and cultural nouns in text-to-image models. |
When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation (2026.findings-acl)
Copied to clipboard
| Challenge: | Preprocessing-based methods for stereotype mitigation are widely used in NLP . preprocessing methods cause unintended shifts in attention flow, authors say . |
| Approach: | They propose to use preprocessing-based methods to reduce stereotypes for targeted groups . they find that stereotyping or counter-stereotyping can increase for other demographics . |
| Outcome: | The proposed methods often induce unintended shifts across demographics, the authors show . they show that such side effects are not accompanied by large changes in attention flow . |
Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts (D19-1)
Copied to clipboard
Elissa Redmiles, Lisa Maszkiewicz, Emily Hwang, Dhruv Kuchhal, Everest Liu, Miraida Morales, Denis Peskov, Sudha Rao, Rock Stevens, Kristina Gligorić, Sean Kross, Michelle Mazurek, Hal Daumé III
| Challenge: | Despite this, we lack a thorough understanding of how to validly measure readability at scale, especially for domain-specific texts. |
| Approach: | They present a comparison of the validity of well-known readability measures and introduce a novel approach to measure readability at scale. |
| Outcome: | The proposed approach addresses shortcomings of existing measures. |
CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data (2020.lrec-1)
Copied to clipboard
Guillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau, Vishrav Chaudhary, Francisco Guzmán, Armand Joulin, Edouard Grave
| Challenge: | Pre-training text representations have led to significant improvements in many areas of natural language processing. |
| Approach: | They propose a pipeline to extract monolingual datasets from Common Crawl . pipeline follows data processing introduced in fastText that deduplicates documents . |
| Outcome: | The proposed pipeline performs standard document deduplication and language identification similar to the pipeline introduced in fastText and a filtering step to select documents close to high quality corpora like Wikipedia. |
TWEETQA: A Social Media Focused Question Answering Dataset (P19-1)
Copied to clipboard
Wenhan Xiong, Jiawei Wu, Hong Wang, Vivek Kulkarni, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang
| Challenge: | Social media is becoming an important realtime information source, especially during natural disasters and emergencies. |
| Approach: | They present a large-scale dataset for question answering over social media data . they gather tweets used by journalists and ask human annotators to write questions upon them . |
| Outcome: | The proposed dataset shows that neural models that perform well on formal texts are limited in their performance . the proposed model is still lagging behind human performance with a large margin . |
Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Question Answering models typically use retrieval and reasoning components to identify relevant information for reasoning. |
| Approach: | They propose a retrieval parameterization method that marginalizes unanswerable queries . they show that marginalization allows a model to mitigate false negatives in annotations . |
| Outcome: | The proposed model improves on two multi-document question answering datasets and shows that marginalization improves performance. |
GeBioToolkit: Automatic Extraction of Gender-Balanced Multilingual Corpus of Wikipedia Biographies (2020.lrec-1)
Copied to clipboard
| Challenge: | a tool for extracting multilingual parallel corpora at sentence level with document and gender information from Wikipedia biographies. |
| Approach: | They propose a tool for extracting multilingual parallel corpora at sentence level with document and gender information from Wikipedia biographies. |
| Outcome: | The proposed tool extracts a corpus of 2,000 sentences in English, Spanish and Catalan. |
Flexible Generation of Natural Language Deductions (2021.emnlp-main)
Copied to clipboard
| Challenge: | Developing models that can make useful inferences from natural language premises has been a core goal in artificial intelligence since the field's early days. |
| Approach: | They propose a method for building models to generate deductive inferences from diverse natural language inputs without direct human supervision. |
| Outcome: | The proposed model is more accurate and flexible than baseline systems. |
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)
Copied to clipboard
| Challenge: | Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans. |
| Approach: | They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. |
| Outcome: | The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans. |
Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge-based visual question answering systems rely on Concept-Net and Wikipedia to obtain external knowledge. |
| Approach: | They propose a visual retriever-reader pipeline that uses a natural language knowledge base and a Visual retriever to retrieve relevant knowledge. |
| Outcome: | The proposed method significantly improves the visual retriever-reader pipeline on the OK-VQA benchmark. |
Design Challenges in Low-resource Cross-lingual Entity Linking (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing techniques for grounding mentions of entities in a foreign language do not rise to the challenges introduced by text in low-resource languages (LRL) and fail to generalize to text not taken from Wikipedia, on which they are usually trained. |
| Approach: | They propose a cross-lingual XEL technique that uses search engines to locate and search for foreign language entries in Wikipedia. |
| Outcome: | The proposed system shows an increase of 25% in gold candidate recall and 13% in end-to-end linking accuracy over state-of-the-art baselines. |
WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking (2020.coling-main)
Copied to clipboard
| Challenge: | Using a neural reranking model, we can match a UMLS concept with a Wikipedia page, enabling manual alignment with minimal effort. |
| Approach: | They propose a cross-lingual neural reranking model to match a UMLS concept with a Wikipedia page, which achieves a recall@1of 72%, a substantial improvement of 20% over word- and char-level BM25. |
| Outcome: | The proposed model achieves recall@1of 72%, 20% better than word- and char-level BM25, and will facilitate easier access to Wikipedia for health professionals, patients, and NLP systems, including in multilingual settings. |
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for entity representations do not capture information in a knowledge base, and cannot represent entities that do not exist in the KB. |
| Approach: | They propose a pretrained contextualized representation of words and entities based on the bidirectional transformer. |
| Outcome: | The proposed model achieves impressive empirical performance on a wide range of entity-related tasks. |
MultiHoax: A Dataset of Multi-hop False-premise questions (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on single-hop FPQs, but real-world reasoning often requires multi-hop inference . state-of-the-art LLMs struggle to detect false premises across different countries, knowledge categories, and multi-step reasoning types. |
| Approach: | They propose a benchmark to evaluate Large Language Models' ability to handle false premises in complex, multi-step reasoning tasks. |
| Outcome: | The proposed tests show that state-of-the-art LLMs struggle to detect false premises across different countries, knowledge categories, and multi-hop reasoning types. |
It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution (D19-1)
Copied to clipboard
| Challenge: | Existing attempts to mitigate gender bias rely on operationalisation of gender bias as a projection over a linear subspace. |
| Approach: | They propose to operationalise gender bias as a linear subspace and augmented a corpus to remove bias by swapping all inherently-gendered words in the copy. |
| Outcome: | The proposed approach outperforms projection-based methods at the task of drawing non-biased gender analogies by an average of 19% across both corpora. |
Linking, Searching, and Visualizing Entities in Wikipedia (L18-1)
Copied to clipboard
| Challenge: | Existing systems to extract, index, search, and visualize entities in Wikipedia are not strings, but unique identifiers from Wikidata. |
| Approach: | They propose a system to extract, index, search, and visualize entities in Wikipedia . they use a document model to store linguistic annotations and a string matching engine . |
| Outcome: | The proposed system achieves CEAFm scores of 70.0 on English, 64.4 on Chinese, and 66.5 on Spanish. |
Exploring Hint Generation Approaches for Open-Domain Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing automatic question answering systems rely on contextual information to provide accurate answers. |
| Approach: | They propose a context preparation approach that uses Automatic Hint Generation techniques to generate hints instead of retrieved contexts. |
| Outcome: | The proposed approach surpasses retrieval-based and generation-based methods on three QA datasets. |
Lexical Knowledge Internalization for Neural Dialog Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge-grounded dialog models ignore the knowledge that resides in people's minds during a conversation. |
| Approach: | They propose to integrate lexical knowledge internally into the model's parameters instead of further conditioning them on external knowledge . they adopt contrastive learning approach and use a dictionary-based token-level lexicon retriever that requires only weak supervision. |
| Outcome: | The proposed model can relate J.K Rowling to Khalsa Aid with the knowledge retrieved from Wikipedia. |
Extracting an English-Persian Parallel Corpus from Comparable Corpora (L18-1)
Copied to clipboard
| Challenge: | Existing methods to extract parallel sentences from Wikipedia are limited for some language pairs such as Persian-English. |
| Approach: | They propose a bidirectional method to extract parallel sentences from Wikipedia . they add extracted sentences to existing training data and use IR system to measure similarity . |
| Outcome: | The proposed method outperforms the one-directional approach in analyzing translation data from two translation systems and IR systems. |
Learning Word Vectors for 157 Languages (L18-1)
Copied to clipboard
| Challenge: | Distributed word representations, or word vectors, have been used in natural language processing for many tasks. |
| Approach: | They propose to use the encyclopedia Wikipedia and the common crawl corpus to train distributed word representations on large corpora and use them in downstream tasks. |
| Outcome: | The proposed model performs very well on 10 languages for which evaluation dataset exists. |
LinkBERT: Pretraining Language Models with Document Links (2022.acl-long)
Copied to clipboard
| Challenge: | Existing language model pretraining methods do not capture dependencies or knowledge that span across documents. |
| Approach: | They propose a language model pretraining method that leverages links between documents . they use masked language modeling and document relation prediction to model LMs . |
| Outcome: | The proposed method outperforms existing methods on downstream tasks across two domains. |
VeriScore: Evaluating the factuality of verifiable claims in long-form text generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing metrics for evaluating the factuality of long-form text assume that every claim is verifiable. |
| Approach: | They propose a metric to evaluate factuality in diverse long-form generation tasks . they use open-weight language models to extract verifiable and unverifiably content . |
| Outcome: | The proposed metric can be implemented with either closed or fine-tuned open-weight language models. |
Generating Fact Checking Briefs (2020.emnlp-main)
Copied to clipboard
Angela Fan, Aleksandra Piktus, Fabio Petroni, Guillaume Wenzek, Marzieh Saeidi, Andreas Vlachos, Antoine Bordes, Sebastian Riedel
| Challenge: | Existing work has framed fact checking as classification, often supported by a claim as input. |
| Approach: | They propose to use natural language briefs to increase the accuracy of fact checking . they show that QABriefer increases the accuracy by 10% while QABries reduce time . |
| Outcome: | The proposed model increases the accuracy of crowdworkers by 10% while reducing the time required by 20%. |
Coverage of Information Extraction from Sentences and Paragraphs (D19-1)
Copied to clipboard
| Challenge: | Textual information extraction (IE) uses textual features to negate stronger statements, such as the negation of stronger statements. |
| Approach: | They propose to use textual features to predict whether a given text segment mentions all objects standing in a certain relationship with a subject. |
| Outcome: | The proposed features can predict whether a given text segment mentions all objects standing in a certain relationship with a particular subject. |
Improving Unsupervised Keyphrase Extraction using Background Knowledge (L18-1)
Copied to clipboard
| Challenge: | Existing methods of keyphrase extraction are supervised and unsupervised . Topical PageRank uses topical information to extract the top topics of a document . |
| Approach: | They propose an unsupervised method for keyphrase extraction based on Wikipedia . they construct a semantic graph and transform the extraction problem into an optimization problem . |
| Outcome: | The proposed method improves over other state-of-the-art models by more than 2% in F1-score. |
WikiDragon: A Java Framework For Diachronic Content And Network Analysis Of MediaWikis (L18-1)
Copied to clipboard
| Challenge: | WikiDragon is a Java Framework designed to give developers in computational linguistics an intuitive API to build, parse and analyze instances of MediaWikis. |
| Approach: | They introduce WikiDragon, a Java Framework that allows developers to build, parse and analyze instances of MediaWikis on their computers. |
| Outcome: | The framework is based on the Wikipedia, Wiktionary, WikiSource or WikiNews and evaluates link extraction, diachronic network analysis and the impact of different frameworks to text analysis. |
SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages (2023.acl-long)
Copied to clipboard
| Challenge: | Prior work on document-level simplification has focused on sentence-level edits, while many desirable edits require document- level context. |
| Approach: | They propose a dataset that reconstructs the document-level editing process from English Wikipedia to paired Simple Wikipedia articles. |
| Outcome: | The proposed dataset reconstructs the document-level editing process from English Wikipedia (EW) articles to paired Simple Wikipedia (SEW) pages. |
Aligning Wikipedia with WordNet:a Review and Evaluation of Different Techniques (2020.lrec-1)
Copied to clipboard
| Challenge: | a reliable alignment between WordNet and Wikipedia is a valuable resource for the creation of new wordnets in other languages and for the development of existing wordnet. |
| Approach: | They evaluate methods for aligning Wikipedia articles with WordNet synsets . they use a new gold and silver standard and a method that creates wordnets in other languages . |
| Outcome: | The proposed methods can be used to evaluate the quality of alignments between Wikipedia and WordNet synsets. |
Harvesting and Refining Question-Answer Pairs for Unsupervised QA (2020.acl-main)
Copied to clipboard
| Challenge: | Recent research attempts to extend unsupervised question answering to settings with few or no labeled data available. |
| Approach: | They propose two approaches to improve unsupervised question answering . first, they harvest lexically and syntactically divergent Wikipedia questions to automatically construct a corpus of question-answer pairs . second, they take advantage of the QA model to extract more appropriate answers . |
| Outcome: | The proposed approach outperforms previous unsupervised approaches by a large margin and is competitive with early supervised models. |
Developing a Dataset of Overridden Information in Wikipedia (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to detect information overridden by the Web are not accurate and require a user's perspective to make the decision. |
| Approach: | They propose a task to detect whether a reference sentence has overridden a target sentence by using sentence pairs from the difference between two versions of Wikipedia. |
| Outcome: | The proposed task is formalized as a binary classification problem to determine whether a reference sentence has overridden a target sentence. |
Bridging Background Knowledge Gaps in Translation with Automatic Explicitation (2023.emnlp-main)
Copied to clipboard
| Challenge: | despite its potential to help users, NLP research on explicitation is limited because of the lack of adequate evaluation methods. |
| Approach: | They propose automatic methods to generate explicitations from a Wikipedia dataset . they use both intrinsic and extrinsic evaluation to evaluate the system's effectiveness . |
| Outcome: | The proposed system bridges the gap between the source speaker and the target audience . it is effective based on intrinsic and extrinsic evaluation, the authors show . |
A Multilingual Dataset for Evaluating Parallel Sentence Extraction from Comparable Corpora (L18-1)
Copied to clipboard
| Challenge: | BUCC Shared Task aims to extract parallel sentences from comparable corporad . resulting corpus contains about 3.5 million distinct sentences in english, french, german, Russian, and Chinese . |
| Approach: | They present challenges faced to build a parallel sentences dataset from comparable corporad . they emphasize issues faced to include Chinese as one of the languages . |
| Outcome: | The 2017 BUCC Shared Task was a first for this task . the dataset contains 3.5 million sentences in English, French, German, Russian, and Chinese . |
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning (D19-1)
Copied to clipboard
| Challenge: | Existing reading comprehension benchmarks do not contain complex coreferential phenomena . obtaining questions focused on such phenomena is difficult because of lexical cues . |
| Approach: | They propose to use a crowdsourced dataset to examine the ability of models to resolve coreference among entities in Wikipedia paragraphs. |
| Outcome: | The proposed model performs significantly worse than humans on the reading comprehension benchmark . paragraphs and other longer texts typically make multiple references to the same entities . |
LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current dense retrievers struggle with queries with logical connectives, a use case that is often overlooked but important in downstream applications. |
| Approach: | They propose a logically-informed contrastive learning objective for dense retrievers that learns to respect the subset and mutually exclusive set relation between query results. |
| Outcome: | The proposed model improves retrieval performance and consistency on entity retrieval tasks. |
Fact or Fiction: Verifying Scientific Claims (2020.emnlp-main)
Copied to clipboard
David Wadden, Shanchuan Lin, Kyle Lo, Lucy Lu Wang, Madeleine van Zuylen, Arman Cohan, Hannaneh Hajishirzi
| Challenge: | SciFact is a dataset of 1.4K expert-written scientific claims paired with evidence-containing abstracts annotated with labels and rationales. |
| Approach: | They construct a dataset of 1.4K scientific claims paired with evidence-containing abstracts annotated with labels and rationales to test their system. |
| Outcome: | The proposed system can verify claims related to COVID-19 by identifying evidence from the CORD-19 corpus. |
Latent Retrieval for Weakly Supervised Open Domain Question Answering (P19-1)
Copied to clipboard
| Challenge: | Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. |
| Approach: | They propose to jointly learn the retriever and reader from question-answer string pairs and without any IR system. |
| Outcome: | The proposed approach outperforms BM25 on open datasets with a learner and reader by 19 points in exact match. |
Classifying Dyads for Militarized Conflict Analysis (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing research examines the origins of militarized conflict by examining bi-lateral relationships between entity pairs and multi-lateral relations among multiple entities. |
| Approach: | They propose to use Wikipedia to model dyadic and systemic causes to compare their correlations with conflict between two entities. |
| Outcome: | The proposed graphs show that Wikipedia articles of allies are semantically more similar than enemies. |
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA (2025.findings-emnlp)
Copied to clipboard
Elisei Rykov, Kseniia Petrushina, Maksim Savkin, Valerii Olisov, Artem Vazhentsev, Kseniia Titova, Alexander Panchenko, Vasily Konovalov, Julia Belikova
| Challenge: | Existing hallucination detection benchmarks operate at the sequence level and are limited to English . Existing methods lacking fine-grained, multilingual supervision are limited in English based on the sequence . |
| Approach: | They propose a large-scale, multilingual dataset annotated with span-level hallucinations across 14 languages. |
| Outcome: | The proposed dataset annotated with span-level hallucinations across 14 languages is scalable and cost-efficient. |
How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases (2023.acl-long)
Copied to clipboard
| Challenge: | a recent study found that pre-training can teach language models to rely on hierarchical syntactic features . aaron ramirez: we find that pretraining on simpler language induces a hierarchic bias . |
| Approach: | They find that pre-training can teach language models to rely on hierarchical syntactic features . authors: this suggests that in cognitively plausible language acquisition settings, models may be more data-efficient . |
| Outcome: | a recent study shows that pre-training can teach language models to rely on hierarchical features . the findings suggest that in plausible language acquisition settings, language models may be more data-efficient than previously thought . |
The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English (D19-1)
Copied to clipboard
Francisco Guzmán, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, Marc’Aurelio Ranzato
| Challenge: | a vast majority of language pairs in the world are considered low-resource because they have little parallel data available. |
| Approach: | They propose to use a dataset to evaluate methods trained on low-resource language pairs . they report baseline performance using supervised, weakly supervised and semi-supervised settings . |
| Outcome: | The proposed evaluation datasets show that current state-of-the-art methods perform poorly on this benchmark, posing a challenge to the research community working on low-resource MT. |
Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity (2020.emnlp-main)
Copied to clipboard
| Challenge: | Open-ended human learning and information-seeking systems often ignore the user’s pre-existing knowledge. |
| Approach: | They propose to use pre-existing user knowledge to build a model that reproduces human assistant policies and improves over a bert content model by 13 mean reciprocal rank points. |
| Outcome: | The proposed model reproduces human assistant policies and improves over a bert content model by 13 mean reciprocal rank points. |
Machine Reading of Historical Events (2020.acl-main)
Copied to clipboard
| Challenge: | Using a short text description of an event, we can extract relevant sentences from Wikipedia and apply a combination of task-specific and general-purpose feature embeddings for the classification. |
| Approach: | They propose to use Wikipedia sentences to extract relevant sentences and apply feature embeddings to the task. |
| Outcome: | The proposed model outperforms the historical event ordering task and the event focus time task in the literature. |
CoDEx: A Comprehensive Knowledge Graph Completion Benchmark (2020.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge graph completion benchmarks for knowledge graphs are often incomplete . however, the field has remained static over the past decade . |
| Approach: | They propose to use Wikidata and Wikipedia to improve on existing benchmarks . they analyze logical relation patterns, then perform baseline link prediction and triple classification . |
| Outcome: | The proposed datasets improve upon existing benchmarks in scope and difficulty. |
Task-Driven and Experience-Based Question Answering Corpus for In-Home Robot Application in the House3D Virtual Environment (2022.lrec-1)
Copied to clipboard
| Challenge: | Question answering is an important part of natural language processing (NLP) |
| Approach: | They propose to use TEQA to investigate the ability of agent task experience understanding for the long-term household task. |
| Outcome: | The proposed corpus aims to investigate the ability of task experience understanding of agents for the daily question answering scenario on the ALFRED dataset. |
MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems (2026.acl-long)
Copied to clipboard
| Challenge: | MONETA is the first multimodal industry classification benchmark with text and geospatial sources. |
| Approach: | They propose a multimodal industry classification benchmark using text and geospatial sources. |
| Outcome: | The proposed model increases the accuracy of the existing models by 22.80%. |
Cross-Dialect Information Retrieval: Information Access in Low-Resource and High-Variance Languages (2025.coling-main)
Copied to clipboard
| Challenge: | lexical gaps between dialects in cross-lingual information retrieval (CLIR) are caused by orthographic variations and different regional expressions. |
| Approach: | They propose a dataset that consists of seven German dialects extracted from Wikipedia. |
| Outcome: | The proposed dataset consists of seven German dialects extracted from Wikipedia. |
Enriching a Lexicon of Discourse Connectives with Corpus-based Data (L18-1)
Copied to clipboard
| Challenge: | Existing annotation efforts for multiple languages have focused on discourse connectives, but we have limited it to the class of connectives marking contrast and the additional relations such connectives might convey. |
| Approach: | They enrich a lexicon of italian COnnectives with real corpus data for connectives marking contrast relations in text. |
| Outcome: | The proposed resource is a valuable tool for linguistic analyses of discourse relations and the training of a classifier for NLP applications. |
SpEL: Structured Prediction for Entity Linking (2023.emnlp-main)
Copied to clipboard
| Challenge: | Entity linking is a key component of structured data creation by linking spans of text to an ontology or knowledge source. |
| Approach: | They propose to use structured prediction for entity linking to classify each input token as an entity and aggregate the token predictions. |
| Outcome: | The proposed system outperforms the state-of-the-art on the commonly used AIDA benchmark dataset for entity linking to Wikipedia. |
English Machine Reading Comprehension Datasets: A Survey (2021.emnlp-main)
Copied to clipboard
| Challenge: | a survey of English Machine Reading Comprehension datasets is carried out . the aim is to provide a concise yet informative overview of the landscape . |
| Approach: | They survey 60 English Machine Reading Comprehension datasets to provide a resource for other researchers interested in this problem. |
| Outcome: | The proposed survey covers 60 English MRC datasets with a view to providing a resource for other researchers interested in the problem. |
A Short Survey on Sense-Annotated Corpora (2020.lrec-1)
Copied to clipboard
| Challenge: | Word Sense Disambiguation (WSD) is a key task in Natural Language Understanding. |
| Approach: | They propose to use sense-annotated corpora for supervised Word Sense Disambiguation. |
| Outcome: | The proposed methods have been compared with knowledge-based approaches and have shown to be more efficient when they are available. |
Neural CRF Model for Sentence Alignment in Text Simplification (2020.acl-main)
Copied to clipboard
| Challenge: | Text simplification systems are based on the quality and quantity of complex-simple sentence pairs extracted by aligning sentences between parallel articles. |
| Approach: | They propose a neural CRF alignment model which leverages the sequential nature of sentences in parallel documents and utilizes a sentence pair model to capture semantic similarity. |
| Outcome: | The proposed model outperforms previous work on monolingual sentence alignment task by more than 5 points in F1. |
Soft Gazetteers for Low-Resource Named Entity Recognition (2020.acl-main)
Copied to clipboard
| Challenge: | Existing named entity recognition models use gazetteers to improve performance, but they are limited in coverage and do not exist in low-resource languages. |
| Approach: | They propose a method that integrates Wikipedia information into named entity models by cross-lingual entity linking. |
| Outcome: | The proposed method improves on four low-resource languages with Wikipedia . it incorporates available information from english knowledge bases into neural models . |
Partially-Aligned Data-to-Text Generation with Distant Supervision (2020.emnlp-main)
Copied to clipboard
| Challenge: | Using partially-aligned data is an alternative way of solving the dataset scarcity problem. |
| Approach: | They propose a task to generate human-readable text for describing some given structured data enabling more interpretability. |
| Outcome: | The proposed framework outperforms baseline models and validates the feasibility of using partially-aligned data. |
Models and Datasets for Cross-Lingual Summarisation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent years have witnessed increased interest in abstractive summarisation thanks to the popularity of neural network models and the availability of datasets containing hundreds of thousands of document-summary pairs. |
| Approach: | They propose to create a cross-lingual summarisation corpus with long documents in a source language associated with multi-sentence summaries in . target language. |
| Outcome: | The proposed task can be applied to several other languages and covers twelve languages and directions. |
HelloFresh: LLM Evalutions on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits (2024.findings-acl)
Copied to clipboard
Tim Franzmeyer, Aleksandar Shtedritski, Samuel Albanie, Philip Torr, Joao F. Henriques, Jakob Foerster
| Challenge: | a better understanding of LLM capabilities on real world tasks is vital for safe development and deployment. |
| Approach: | They propose a new LLM called HelloFresh that uses real-world data to measure performance . they backtest the model and find it yields a temporally consistent ranking . |
| Outcome: | The proposed benchmarks outperform static evaluation data and test data on Wikipedia pages. |
DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking (2020.acl-main)
Copied to clipboard
Christopher Hidey, Tuhin Chakrabarty, Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab, Smaranda Muresan
| Challenge: | Fact Extraction and Verification datasets provide a resource for end-to-end fact-checking, requiring retrieval of evidence from Wikipedia to validate a veracity prediction. |
| Approach: | They propose a system that is resilient to attacks by multiple propositions, temporal reasoning, ambiguity and lexical variation and a sequence of evidence sentences and veracity relation predictions. |
| Outcome: | The proposed system is resilient to three realistic “attacks” and obtains state-of-the-art results due to improved evidence retrieval. |
Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection (2026.acl-long)
Copied to clipboard
Yuwei Zhang, Wenhao Yu, Shangbin Feng, Yifan Zhu, Letian Peng, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang
| Challenge: | Existing knowledge injection benchmarks for large language models lack standardized testing grounds. |
| Approach: | They propose a knowledge injection benchmark that leverages recently-added and expert-curated facts from Wikipedia’s “Did You Know...” entries. |
| Outcome: | The proposed framework improves reliability accuracy by 29.1%. |
Retrieval Augmented Visual Question Answering with Outside Knowledge (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent systems that use Dense Passage Retrieval (DPR) for visual question answering use Denses trained separately from answer generation. |
| Approach: | They propose a joint training scheme that integrates DPR with answer generation to improve the performance of OK-VQA systems. |
| Outcome: | The proposed model outperforms existing systems with strong Dense Passage Retrieval (DPR) it yields significant improvements in answer quality and computation required for training. |
To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in open-domain question answering have demonstrated impressive accuracy on general-purpose domains like Wikipedia. |
| Approach: | They propose a more realistic end-to-end domain shift evaluation setting covering five diverse domains to assess model adaption. |
| Outcome: | The proposed model improves by 24 points when adapted to unsupervised datasets. |
Italian Word Embeddings for the Medical Domain (2024.lrec-main)
Copied to clipboard
| Challenge: | Neural word embeddings have proven valuable in the development of medical applications, but for the Italian language, there are no publicly available corpora, embedds, or evaluation resources tailored to this domain. |
| Approach: | They propose to use a corpus of medical texts to generate neural word embeddings in Italian using Metathesaurus concept graphs. |
| Outcome: | The results show that the new embeddings correlate well with human judgments regarding similarity and relatedness of medical concepts. |
Real World Conversational Entity Linking Requires More Than Zero-Shots (2024.findings-acl)
Copied to clipboard
| Challenge: | Entity linking (EL) in conversations is a key component of many downstream tasks such as semantic search. |
| Approach: | They propose to use Fandom and Wikipedia to evaluate EL models' ability to generalize to a new unfamiliar KB without prior training. |
| Outcome: | The proposed evaluation framework and dataset are tailored to facilitate the study. |
RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) enhances large language models by integrating external knowledge retrieved at inference time. |
| Approach: | They evaluate RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge. |
| Outcome: | The proposed approach improves performance on knowledge-intensive NLP tasks. |
Bias Neutralization in Non-Parallel Texts: A Cyclic Approach with Auxiliary Guidance (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for subjective bias neutralization rely on parallel text training and lose important bias-independent context. |
| Approach: | They propose a bias neutralization model that uses an auxiliary guided cycle consistent GAN to train with a combination of adversarial, cycleconsistency and identity mapping loss. |
| Outcome: | The proposed model significantly improves subjective bias neutralization compared to existing methods. |
Filling the Temporal Void: Recovering Missing Publication Years in the Project Gutenberg Corpus Using LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Currently, there is no publicly available corpus for diachronic text analysis due to the lack of accurate temporal metadata. |
| Approach: | They propose to add missing temporal metadata to the Gutenberg corpus by using open web, Wikipedia, and Open Library API sources. |
| Outcome: | The proposed corpus includes 53,774 books with a total of 3.8 billion tokens in 11 languages, produced between 1600 and 2000. |
From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Adapting cultural values in Large Language Models presents significant challenges due to biases and data limitations. |
| Approach: | They propose to augment World Values Survey (WVS) data with encyclopedic and scenario-based cultural narratives from Wikipedia and NormAd to address these limitations. |
| Outcome: | The proposed approach enhances cultural distinctiveness and improves classification performance across cultures. |
Linking Named Entities in Diderot’s Encyclopédie to Wikidata (2024.lrec-main)
Copied to clipboard
| Challenge: | Encyclopédie was published between 1751 and 1772 and aimed to collect the knowledge of its time. |
| Approach: | They describe the annotation of more than 9,100 Encyclopédie entries with Wikidata identifiers . they extract all geographic entries and annotate 8,300 entries having a geographic content only. |
| Outcome: | The annotation process and application examples are presented in this paper. |
Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | prevailing view in language acquisition research has long held that child-directed language is more effective than adultdirected language (ADL) |
| Approach: | They propose a frequency-controlled testing methodology to enable balanced comparisons across training corpora. |
| Outcome: | The proposed method outperforms models trained on English Child-Directed Language (CDL) but it does not yield stronger generalizations for acquiring syntax. |
Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated remarkable generalization abilities in mathematics and reasoning tasks. |
| Approach: | They pre-trained decoder-based language models from scratch using ten programming languages and three natural language datasets. |
| Outcome: | The proposed models outperform natural languages on logical reasoning tasks. |
Detecting Sockpuppetry on Wikipedia Using Meta-Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to model author-specific sockpuppet detection on Wikipedia are limited in data-scarce settings. |
| Approach: | They propose to use meta-learning to improve model adaptation to a new sockpuppet-group by training models across multiple tasks. |
| Outcome: | The proposed technique improves performance in data-scarce settings by training models across multiple tasks. |
Lemmatization of Polish Multi-word Expressions (2025.emnlp-main)
Copied to clipboard
| Challenge: | PolEval task is complicated by linguistic irregularities and historical factors. |
| Approach: | They propose to use fine-tuned plT5 and mT5 models to improve lemmatization of multi-word expressions and proper names in Polish instead of rule-based methods. |
| Outcome: | The proposed model achieved 86.23% AccCS, 89.43% accCI and 88.79% on a gold-standard dataset derived from Wikipedia . |
Is Child-Directed Speech Effective Training Data for Language Models? (2024.emnlp-main)
Copied to clipboard
| Challenge: | High-performing language models are typically trained on hundreds of billions of words, but human learners use language fluently after far less training data. |
| Approach: | They train GPT-2 and RoBERTa models on 29M words of English child-directed speech and a new matched, synthetic dataset. |
| Outcome: | The proposed models show that child language input is not valuable for training language models. |
Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia (2024.emnlp-main)
Copied to clipboard
| Challenge: | a new task for entity insertion in information networks is needed to integrate entities into multilingual linked corpora . text spans in the source and target entities are not available to insert a link to the target entity . a benchmark dataset in 105 languages is used to study the problem of entity inserted in information systems . |
| Approach: | They propose a framework for entity insertion that integrates entities into linked corpora . they compile a benchmark dataset in 105 languages and test it in a zero-shot manner . |
| Outcome: | The proposed framework outperforms baseline models on languages not seen during training with minimal performance drop. |
Unequal Scientific Recognition in the Age of LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new study evaluates the extent to which popular and frontier LLMs recognize scientists . recognition of scientists remains uneven across gender and geography . |
| Approach: | They evaluate the extent to which popular and frontier LLMs recognize scientists . they compare their outputs against OpenAlex and Wikipedia . |
| Outcome: | The proposed models show that they exhibit selective and inconsistent recognition patterns . women researchers and researchers from Africa, Asia, and Latin America are significantly underrecognized . |
Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages (2026.acl-long)
Copied to clipboard
| Challenge: | Existing research has largely overlooked lower-resource languages for automated fact-checking. |
| Approach: | They propose a multilingual CND corpus spanning 18 languages across three resource levels and a small decoder-based language model for CND. |
| Outcome: | The proposed model outperforms prompted LLMs in cross-lingual CND across languages. |
Enhancing RAG Efficiency with Adaptive Context Compression (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods apply fixed compression rates, over-compressing simple queries or under-compressed complex ones. |
| Approach: | a new framework uses a hierarchical compressor and a context selector to optimize inference efficiency . a framework that dynamically adjusts compression rates based on input complexity optimizes inference without loss of accuracy. |
| Outcome: | Adaptive Context Compression for RAG outperforms fixed-rate methods on Wikipedia and five QA datasets . |
The Million Authors Corpus: A Cross-Lingual and Cross-Domain Wikipedia Dataset for Authorship Verification (2025.findings-acl)
Copied to clipboard
| Challenge: | Authorship verification (AV) is a crucial task for identity verification, accountlinking, historical linguistics, and AI-generated text identification. |
| Approach: | They propose to use Wikipedia's Million Authors Corpus to examine authorship verification models on a broad scale. |
| Outcome: | The proposed dataset includes 60.08M textual chunks, contributed by 1.29M Wikipedia authors. |
How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP (2026.acl-long)
Copied to clipboard
Kushal Tatariya, Artur Kulmizev, Wessel Poelman, Esther Ploeger, Marcel Bollmann, Johannes Bjerva, Jiaming Luo, Heather Lent, Miryam de Lhoneux
| Challenge: | Wikipedia’s perceived high quality and broad language coverage have established it as a fundamental resource in NLP. |
| Approach: | They propose a data filtering procedure which removes a large percentage of Wikipedia's data and a 4-level quality ranking of the site. |
| Outcome: | The results show that the proposed filtering procedure outperforms the raw Wikipedia models in three language modelling scenarios. |
MessIRve: A Large-Scale Spanish Information Retrieval Dataset (2025.emnlp-main)
Copied to clipboard
Francisco Valentini, Viviana Cotik, Damián Furman, Ivan Bercovich, Edgar Altszyler, Juan Manuel Pérez
| Challenge: | Information retrieval (IR) is the task of finding relevant documents in response to a user query. |
| Approach: | They propose a large-scale Spanish IR dataset with almost 700,000 queries from Google’s autocomplete API and relevant documents sourced from Wikipedia. |
| Outcome: | The proposed dataset covers a wide variety of topics, unlike smaller datasets. |
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining (2025.acl-long)
Copied to clipboard
Jeffrey Li, Mohammadreza Armandpour, Seyed Iman Mirzadeh, Sachin Mehta, Vaishaal Shankar, Raviteja Vemulapalli, Samy Bengio, Oncel Tuzel, Mehrdad Farajtabar, Hadi Pouransari, Fartash Faghri
| Challenge: | Large language models (LLMs) trained on historical web data inevitably become outdated. |
| Approach: | They propose a web-scale dataset for time-continual pretraining of LLMs derived from 114 dumps of Common Crawl (CC) they also design time-stratified evaluations to assess how well various continual learning methods adapt to new data while retaining past knowledge. |
| Outcome: | The proposed benchmarks show that autoregressive meta-schedules combined with a fixed-ratio replay of older data can achieve comparable held-out loss to re-training from scratch, while requiring significantly less computation (2.6x). |
Concept-pedia: a Wide-coverage Semantically-annotated Multimodal Dataset (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current evaluations for Vision-language Models remain heavily anchored to ImageNet . |
| Approach: | They propose a large-scale semantically-annotated multimodal resource that extends the range of visual concepts, including diverse abstract categories. |
| Outcome: | The proposed model expands the range of visual concepts, including diverse abstract categories. |
RAED: Retrieval-Augmented Entity Description Generation for Emerging Entity Linking and Disambiguation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Entity Linking and Entity Disambiguation systems assume static knowledge bases are incomplete and up-to-date, rendering them incapable of handling entities not yet included in the knowledge base. |
| Approach: | They propose a model that retrieves external knowledge to improve factual grounding in entity descriptions. |
| Outcome: | The proposed model outperforms systems that require fixed knowledge sets on Entity Disambiguation and Wikipedia to improve factual grounding in entity descriptions. |
Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications (2026.findings-acl)
Copied to clipboard
| Challenge: | Text revision is a core process in document creation, capturing how authors iteratively refine, reorganize, and improve written content. |
| Approach: | They synthesize text revision research through the lens of edit intentions . they review prior work across the revision workflow including corpus construction, edit intention taxonomies, edit intentions, and edit intention identification. |
| Outcome: | The proposed approach synthesizes datasets, taxonomies, identification methods, and applications and highlights key open research directions. |
Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models (2025.emnlp-main)
Copied to clipboard
Sina Semnani, Jirayu Burapacheep, Arpandeep Khatua, Thanawan Atchariyachanvanit, Zheng Wang, Monica Lam
| Challenge: | a new study examines the accuracy of Wikipedia's factual inconsistencies . a corpus-level inconsistent detection system can help editors identify inconsistances . |
| Approach: | They propose a corpus-level inconsistency detection system that combines LLM reasoning with retrieval to detect and contextualize potential contradictions for human review. |
| Outcome: | The proposed system can detect inconsistencies in Wikipedia and human review. |