Papers with English language
Improving and Simplifying Template-Based Named Entity Recognition (2023.eacl-srw)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is traditionally approached as a sequence labeling task where a tag is predicted for each token. |
| Approach: | They propose to convert a Named Entity Recognition task into a seq2seq task by generating synthetic sentences using templates. |
| Outcome: | The proposed model outperforms the current state-of-the-art approach in resource-rich, low resource and domain transfer settings and the negative examples play an important role in its performance. |
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing models for the English language have been used to train on large corpus of high-quality texts. |
| Approach: | They present a pretrained Transformer-based encoder-decoder model for the Vietnamese language . they benchmark ViT5 on two downstream text generation tasks . |
| Outcome: | The proposed model outperforms existing models on Vietnamese Abstractive Summarization and Named Entity Recognition tasks. |
Hate Speech Classifiers Learn Normative Social Stereotypes (2023.tacl-1)
Copied to clipboard
| Challenge: | Social stereotypes negatively impact individuals’ judgments about different groups and may have a critical role in understanding language directed toward marginalized groups. |
| Approach: | They first investigate the impact of novice annotators’ stereotypes on their hate-speech-annotation behavior. Then, they examine the effect of normative stereotypes in language on the aggregated annotated judgments. |
| Outcome: | The framework provides insights into sources of bias in hate-speech moderation, informing ongoing debates regarding machine learning fairness. |
LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations (D19-3)
Copied to clipboard
| Challenge: | LINSPECTOR WEB is an open source multilingual inspector to analyze word embeddings. |
| Approach: | They propose to use LINSPECTOR WEB to analyze word embeddings in 28 languages. |
| Outcome: | The system performs 16 simple linguistic probing tasks for a diverse set of 28 languages. |
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. |
Local Structure Matters Most in Most Languages (2022.aacl-short)
Copied to clipboard
| Challenge: | Recent perturbation studies have found unintuitive results on what does and does not matter when performing Natural Language Understanding (NLU) tasks in English. |
| Approach: | They replicate a study on the importance of local structure and relative unimportance of global structure in a multilingual setting. |
| Outcome: | The proposed model replicates a study on the importance of local structure and relative unimportance of global structure in a multilingual setting. |
MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for detecting social-media texts are limited to the English language and longer texts are not easily recognisable by humans. |
| Approach: | They propose to use a multilingual and multi-platform dataset to compare machine-generated text detection methods in the social-media domain to compare them to human-written texts. |
| Outcome: | The proposed dataset contains 472,097 texts, of which about 58k are human-written and approximately the same amount is generated by each of 7 multilingual LLMs. |
Distilling the Knowledge of Romanian BERTs Using Multiple Teachers (2022.lrec-1)
Copied to clipboard
Andrei-Marius Avram, Darius Catrina, Dumitru-Clementin Cercel, Mihai Dascalu, Traian Rebedea, Vasile Pais, Dan Tufis
| Challenge: | Existing approaches to train pre-trained language models focus on the English language, thus widening the gap when considering low-resource languages. |
| Approach: | They propose three versions of distilled BERT models for the Romanian language . they argue that the models offer performance comparable to their teachers . |
| Outcome: | The proposed models perform comparable to their teachers, while being twice as fast on a GPU and 35% smaller. |
A Survey on Multilingual Mental Disorders Detection from Social Media Data (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing studies on mental disorders focus on English data, overlooking critical signals that may be present in non-English texts. |
| Approach: | They present a list of 108 social media datasets that can be used to train NLP models for mental health screening in 25 languages. |
| Outcome: | The proposed datasets cover 25 languages and can be used to train models for mental health screening. |
Safety of Large Language Models Beyond English: A Systematic Literature Review of Risks, Biases, and Safeguards (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have a growing number of applications that generate harmful, biased, or unsafe content. |
| Approach: | They synthesize findings from recent studies that evaluate their robustness across languages . they highlight gaps in multilingual safety research and recommend future work . |
| Outcome: | The systematic review examines the multilingual safety of large language models in English . it identifies challenges such as dataset availability and evaluation biases . |
Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education (2025.naacl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have potential to automate hiring but inherent biases may lead to unfair hiring practices. |
| Approach: | They evaluate how factors such as gender, race, and educational background influence model decisions. |
| Outcome: | The proposed model reduces biases related to gender and race, but implicit biase concerning educational background remains significant. |
TIMERS: Document-level Temporal Relation Extraction (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for temporal relation extraction focus on extracting temporal relations between event pairs present in the same sentence or adjacent sentences, mostly ignoring document-level pairs. |
| Approach: | They propose a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language that leverages rhetorical discourse features and temporal arguments from semantic role labels. |
| Outcome: | The proposed model outperforms previous methods on the TDDiscourse, TimeBank-Dense, and MATRES datasets due to its discourse-level modeling. |
ViDeBERTa: A powerful pre-trained language model for Vietnamese (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing models for Vietnamese that perform well on downstream tasks, such as Question answering, are based on Transformer. |
| Approach: | They propose a pre-trained monolingual Vietnamese model with three versions . they fine-tune and evaluate the model on three important natural language downstream tasks, Part-of-speech tagging, Named-entity recognition, and Question answering. |
| Outcome: | The proposed model outperforms the existing model on three important natural language downstream tasks, Part-of-speech tagging, Named-entity recognition, and Question answering. |
NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification (2023.acl-short)
Copied to clipboard
| Challenge: | Africa has over 2000 indigenous languages but they are under-represented in NLP research due to lack of datasets. |
| Approach: | They propose to use a dataset to classify sentiments for cross-domain adaptation for Nigerian and other African languages. |
| Outcome: | The proposed dataset compares the performance of cross-domain adaptation from Twitter domain and cross-lingual adaptation from English domain. |
Cross-Lingual Knowledge Transfer for Clinical Phenotyping (2022.lrec-1)
Copied to clipboard
Jens-Michalis Papaioannou, Paul Grundmann, Betty van Aken, Athanasios Samaras, Ilias Kyparissidis, George Giannakoulas, Felix Gers, Alexander Loeser
| Challenge: | Current models for clinical phenotyping are limited to clinical notes written in English due to the large amount of labeled and unlabeled clinical text resources. |
| Approach: | They propose to use translation-based methods with domain-specific encoders and cross-lingual encoder plus adapters to perform this task for clinics that do not use the English language. |
| Outcome: | The proposed strategies outperform the state-of-the-art models for clinics that do not use the English language and have a small amount of in-domain data available. |
Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on robustness of pretrained multilingual models are limited to the English language. |
| Approach: | They propose to use data augmentation and contrastive loss term to boost robustness of multilingual models in cross-lingual settings. |
| Outcome: | The proposed model outperforms existing models on clean and noisy data in the cross-lingual setting. |
A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluations of attribution methods focus on the English language . plausibility and faithfulness are two main criteria for plausible and faithful attributions . |
| Approach: | They propose a cross-lingual strategy to measure faithfulness based on word alignments. |
| Outcome: | The proposed approach eliminates drawbacks of erasure-based evaluations and provides a multilingual dataset with highlights to support future studies. |
Longtonotes: OntoNotes with Longer Coreference Chains (2023.findings-eacl)
Copied to clipboard
Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum, Mrinmaya Sachan
| Challenge: | Using Ontonotes, documents in certain genres were split into smaller parts for ease of annotation. |
| Approach: | They propose to merge annotations from documents split into smaller parts in Ontonotes for ease of annotation. |
| Outcome: | The proposed corpus restores documents to their original form, revealing dramatic increases in length in certain genres. |
SMHD-GER: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in German (2023.findings-eacl)
Copied to clipboard
| Challenge: | Mental health problems are a challenge to our modern society, and their prevalence is predicted to increase worldwide. |
| Approach: | They propose a large-scale, carefully constructed dataset for MHC detection built on high-precision patterns and the approach proposed for English. |
| Outcome: | The proposed model leverages engineered (psycho-)linguistic features as well as BERT-German to facilitate further research and conduct extensive experiments. |
ELQA: A Corpus of Metalinguistic Questions and Answers about English (2023.acl-long)
Copied to clipboard
| Challenge: | ELQA corpus is metalinguistic—it consists of language about language. |
| Approach: | They present a corpus of questions and answers in and about the English language . they use a free-form question answering task and multiple LLMs to analyze their capacity . |
| Outcome: | The ELQA corpus covers grammar, meaning, fluency, and etymology . the results can be used to investigate metalinguistic capabilities of NLU models . |
Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to increase training data in low-resource domains may not be effective due to data scarcity. |
| Approach: | They propose a method to transform a high-resource domain into a low-resourced domain by changing its style-related attributes to generate synthetic data for training. |
| Outcome: | The proposed method can significantly improve results on five domain pairs under different data regimes. |
Semantically Inspired AMR Alignment for the Portuguese Language (2020.emnlp-main)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) parsers require alignment between nodes and words of the sentence. |
| Approach: | They propose to use a more semantically matched word-concept pair to align graphs with words in Portuguese . they performed intrinsic and extrinsic evaluations and found it outperforms the English alignment strategies. |
| Outcome: | The proposed method outperforms the existing methods for English and achieves competitive results with a parser designed for the Portuguese language. |
ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing explanation datasets for large language models are limited to the English language and general domain, leading to a scarcity of linguistic diversity and a lack of resources in specialized domains, such as medical. |
| Approach: | They propose to use a medical dataset to assess the interpretability of Large Language Models (LLMs) . they propose to analyze medical text and generate rationales for their decisions . |
| Outcome: | The proposed model passes the pharmacist examination with a 75.7% accuracy, while other models like ChatGPT fail. |
Are Text Classifiers Xenophobic? A Country-Oriented Bias Detection Method with Least Confounding Variables (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for detecting biases are biased because of confounding variables . authors propose a method to detect the biased classifier on any type of unlabeled data . |
| Approach: | They propose a method to detect biases of a specific fine-tuned classifier on unlabeled data. |
| Outcome: | The proposed method detects biases on unlabeled data on named entity perturbations . it uses name-entity recognition on target-domain data and morphosynctactically different languages spoken in relation to countries of the target groups . |
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality (2023.acl-long)
Copied to clipboard
Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li
| Challenge: | Current datasets bias in the English language while leaving other languages underexplored. |
| Approach: | They propose a Chinese answer-to-sequence dataset with high quality and large scale . they propose encoding space for two hybrid knowledge resources to convert this task to a graph-totext problem. |
| Outcome: | The proposed method is effective in generating textual descriptions for the Chinese answer-to-sequence dataset. |
Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing datasets for genderstereotypical reasoning are limited and often limited to overly specific phenomena. |
| Approach: | They propose to use GEST to measure gender-stereotypical reasoning in language models and machine translation systems. |
| Outcome: | The proposed dataset contains 16 gender stereotypes compatible with the English language and 9 Slavic languages. |
MaXM: Towards Multilingual Visual Question Answering (2023.findings-emnlp)
Copied to clipboard
Soravit Changpinyo, Linting Xue, Michal Yarom, Ashish Thapliyal, Idan Szpektor, Julien Amelot, Xi Chen, Radu Soricut
| Challenge: | Visual Question Answering (VQA) has been studied in the English language, but in other languages it would require a considerable amount of resources. |
| Approach: | They propose scalable solutions to multilingual visual question answering using an English language framework and an annotation protocol. |
| Outcome: | The proposed framework reduces human annotation efforts and creates a test-only VQA benchmark in 7 languages. |
Cross-Level Semantic Similarity for Serbian Newswire Texts (2022.lrec-1)
Copied to clipboard
| Challenge: | Semantic similarity is a measure of the level of semantic overlap between texts of different lengths. |
| Approach: | They present a cross-level semantic similarity (CLSS) dataset in Serbian and compare it to its English counterpart, SemEval CLSS. They also use pre-trained language models to fine-tune the dataset. |
| Outcome: | The proposed dataset is compared to its preexisting counterpart in English, SemEval CLSS. The results are presented and state-of-the-art pre-trained language models are evaluated on the CLSS task in Serbian. |
Delving Deeper into Cross-lingual Visual Question Answering (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on cross-lingual VQA have reported poor zero-shot transfer performance of current multilingual multimodal Transformers . lack of multilingual resources has hindered development and evaluation of VQA methods beyond the English language . |
| Approach: | They analyze cross-lingual VQA across different question types of varying complexity . they show that simple modifications to the standard training setup can substantially reduce the transfer gap to monolingual English performance. |
| Outcome: | The proposed model significantly reduces the transfer gap to monolingual English performance . the proposed model also improves on question types and languages . |
BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing multilingual evaluation benchmarks focus on IR in the Polish language, but the Polish is a relatively new field due to the limited availability of Polish datasets. |
| Approach: | They propose to establish large-scale resources for IR in the Polish language and translate them into a new benchmark which includes 13 datasets. |
| Outcome: | The proposed benchmarks are based on 13 open IR datasets in Polish and are a pioneering development in this area. |
xGQA: Cross-Lingual Visual Question Answering (2022.findings-acl)
Copied to clipboard
Jonas Pfeiffer, Gregor Geigle, Aishwarya Kamath, Jan-Martin Steitz, Stefan Roth, Ivan Vulić, Iryna Gurevych
| Challenge: | a lack of multilingual multimodal datasets has hindered multimodal vision and language modeling efforts. |
| Approach: | They propose a multilingual evaluation benchmark for the visual question answering task . they extend the established English GQA dataset to 7 typologically diverse languages . |
| Outcome: | The proposed methods outperform current state-of-the-art models in zero-shot cross-lingual settings, but the accuracy remains low across languages. |
Hate-Speech and Offensive Language Detection in Roman Urdu (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on hate-speech and offensive language detection in social media content is mainly focused on the English language. |
| Approach: | They propose to use an annotated dataset to detect hate-speech and offensive language in social media content . they propose to transfer five existing embedding models to Roman Urdu to test their performance . |
| Outcome: | The proposed model outperforms existing methods on RUHSOLD dataset and train domain-specific embeddings on more than 4.7 million tweets. |
A Comprehensive Survey of Contemporary Arabic Sentiment Analysis: Methods, Challenges, and Future Directions (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing literature on Arabic sentiment analysis is limited, compared to high-resourced languages such as English and French. |
| Approach: | They present a systematic review of existing literature on Arabic sentiment analysis focusing on research utilizing deep learning. |
| Outcome: | The proposed methods highlight gaps in the literature on Arabic sentiment analysis and outline promising directions for future research. |
Unified Pre-training for Program Understanding and Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | PLUG is a programming language that is used for programming and language understanding and generation tasks. |
| Approach: | They propose a sequence-to-sequence model that performs a broad spectrum of program and language understanding and generation tasks. |
| Outcome: | The proposed model outperforms or rivals state-of-the-art models on code summarization, code generation, and code translation tasks in seven programming languages. |
Cross-Lingual Leveled Reading Based on Language-Invariant Features (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Leveled reading (LR) aims to automatically classify texts by the cognitive levels of readers. |
| Approach: | They propose to use adversarial training and cross-lingual pre-training methods to transfer LR knowledge from annotated data in resource-rich English to Chinese. |
| Outcome: | The proposed method captures language-invariant features between English and Chinese. |
FQuAD2.0: French Question Answering and Learning When You Don’t Know (2022.lrec-1)
Copied to clipboard
| Challenge: | Question Answering, including Reading Comprehension, has seen significant scientific breakthroughs over the past few years . but most of these breakthroughs are centered on the English language . |
| Approach: | They propose a dataset to train Question Answering models in the French language . they extend the dataset to 17,000+ unanswerable questions annotated adversarially . |
| Outcome: | The proposed dataset makes it possible to train French Question Answering models with the ability to distinguish unanswerable questions from answerable ones. |
Text-to-Text Extraction and Verbalization of Biomedical Event Graphs (2022.coling-1)
Copied to clipboard
| Challenge: | Biomedical events represent complex, graphical, and semantically rich interactions expressed in the scientific literature. |
| Approach: | They propose a framework to solve event extraction and event verbalization with a unified text-to-text approach. |
| Outcome: | The proposed framework achieves greater state-of-the-art performance than single-task competitors and can generate coherent natural language utterances from structured data. |
Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task (2020.coling-main)
Copied to clipboard
| Challenge: | Recent studies have focused on English language and tasks, but few have explored the complexity of a SLU task. |
| Approach: | They propose to explore Neural Networks approaches for a French Spoken Language Understanding task. |
| Outcome: | The proposed approach outperforms classical Neural Network Architectures and achieves state-of-the-art results. |
LSTMs Compose—and Learn—Bottom-Up (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work in NLP shows that LSTMs capture compositional structure in language data. |
| Approach: | They propose to measure the decompositional interdependence between word meanings in an LSTM based on their gate interactions. |
| Outcome: | The proposed model can model syntactic relationships rather than learning the longer-range relations independently. |
RoQLlama: A Lightweight Romanian Adapted Language Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, open-source large language models are limited to tasks involving the English language. |
| Approach: | They propose to use QLoRA to train a Romanian-adapted LLM with 7 billion parameters and quantized to 4 bits to improve model's performance. |
| Outcome: | The proposed model outperforms the other LLMs on four out of the seven tasks investigated using zero-shot prompting. |
Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog (2022.naacl-main)
Copied to clipboard
| Challenge: | Task-oriented dialog (TOD) is arguably one of the most popular natural language processing (NLP) application areas. |
| Approach: | They propose a multilingual multi-domain TOD dataset that spans four languages . they use a framework for multilingual conversational specialization of pretrained language models . |
| Outcome: | The proposed datasets show that they perform better than existing datasets in English . the proposed framework allows for sample-efficient few-shot transfer for TOD tasks . |
Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Rapid advancements in large language models have highlighted the need for robust evaluation frameworks that assess their core capabilities. |
| Approach: | They propose two benchmarks to assess core capabilities of large language models . current benchmarks for Thai focus mainly on traditional NLP tasks . |
| Outcome: | The proposed benchmarks are based on evaluations of various LLMs with multi-lingual capabilities and are publicly available to encourage further research and development for Thai LLM. |
MACRONYM: A Large-Scale Dataset for Multilingual and Multi-Domain Acronym Extraction (2022.coling-1)
Copied to clipboard
Amir Pouran Ben Veyseh, Nicole Meister, Seunghyun Yoon, Rajiv Jain, Franck Dernoncourt, Thien Huu Nguyen
| Challenge: | Acronym extraction is the task of identifying acronyms and their expanded forms in texts . existing AE methods for English are limited to specific languages and domains . |
| Approach: | They propose to annotate 27,200 sentences in 6 different languages and 2 new domains for AE. |
| Outcome: | The proposed dataset shows that AE in different languages and learning settings has unique challenges . |
Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets (2024.lrec-main)
Copied to clipboard
| Challenge: | Distributional Semantics has undergone significant changes with the introduction of contextualized distributional models. |
| Approach: | They compare static and contextual distributional models for Mandarin Chinese . they find that static models are stronger for some of the classical tasks . |
| Outcome: | The proposed models perform better on some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and categorization of words into abstract semantic classes. |
MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments (2023.emnlp-main)
Copied to clipboard
| Challenge: | In the context of the Indian judiciary, there is an additional complexity - Indian legal case judgments are mostly written in complex English due to historical reasons, but a significant portion of India's population lacks a strong command of the English language. |
| Approach: | They propose to summarize Indian legal case judgments in English and Hindi by combining the summaries of 3,122 case judgment from Indian courts into one dataset. |
| Outcome: | The proposed dataset compares the summarization methods with other datasets and shows that the proposed approaches perform better than previous approaches. |
Methods of Automatic Matrix Language Determination for Code-Switched Speech (2024.emnlp-main)
Copied to clipboard
| Challenge: | Code-switching (CS) is the process of speakers switching between two or more languages in spoken or written language. |
| Approach: | They propose to use the Matrix Language Frame theory to describe CS speech . they compare MLID of English/Mandarin and English/Spanish CS to acoustic language identity . |
| Outcome: | The proposed models outperform monolingual models in acoustic language identity recognition tasks. |
CSL: A Large-scale Chinese Scientific Literature Dataset (2022.coling-1)
Copied to clipboard
| Challenge: | Existing datasets centered around the English language restrict development of Chinese scientific NLP. |
| Approach: | They present a large-scale Chinese scientific literature dataset based on Chinese papers . they use semi-structured data as a natural annotation for many supervised NLP tasks . |
| Outcome: | The proposed dataset can serve as a Chinese corpus and perform many supervised tasks. |
Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish (2024.lrec-main)
Copied to clipboard
| Challenge: | Currently, most of the research on misinformation is focused on the English language . however, there is a scarcity of datasets for other languages, including Turkish . |
| Approach: | They propose a dataset that spans multiple domains and incorporates evidence from three Turkish fact-checking organizations. |
| Outcome: | The proposed dataset has the potential to advance research in the Turkish language. |
Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation (2025.findings-naacl)
Copied to clipboard
Luca Moroni, Giovanni Puccetti, Pere-Lluís Huguet Cabot, Andrei Stefan Bejgu, Alessio Miaschi, Edoardo Barba, Felice Dell’Orletta, Andrea Esuli, Roberto Navigli
| Challenge: | Pretrained Large Language Models (LLMs) are mainly designed for the English language, but are not optimized for non-English languages due to language contamination or multilingual pretraining data. |
| Approach: | They propose a method that leverages neural mapping for vocabulary substitution to optimize LLMs for the Italian language. |
| Outcome: | The proposed method reduces token fertility by 25% and improves grounded alignment strategies. |
MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. |
| Approach: | They propose to use Multi-hop Questioning Answering under Knowledge Editing for Arabic Language to update and/or edit prior knowledge and test it via Multi-Hop Question Answering (MQA). |
| Outcome: | The proposed model outperforms baseline models by a significant margin . it can be used to update and/or edit prior knowledge and then test it with MQA . |
DanteLLM: Let’s Push Italian LLM Research Forward! (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models for large language processing in the English language are limited in resources and evaluation tools for non-English languages. |
| Approach: | They propose a benchmark and an open LLM Leaderboard to evaluate LLMs’ performance in Italian and propose 'DanteLLM' it is the most performant LLM in the world, with improvements of up to 6 points . |
| Outcome: | The proposed model outperforms existing models in Italian and offers a blueprint for the development and evaluation of LLMs in other languages. |
Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a study focuses on evaluating watermarking methods for the English language . the literature for evaluating cross-lingual watermarks is scarce . |
| Approach: | They evaluate representative watermarking methods in four different languages . they examine the quality of text under different watermark procedures . |
| Outcome: | The proposed method is compared with other evaluation methods in four different languages. |
MultiCMET: A Novel Chinese Benchmark for Understanding Multimodal Metaphor (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on multimodal metaphors does not address categorizing the source and target domains in metaphors beyond the English language. |
| Approach: | They propose a Cascading Domain Knowledge Integration benchmark to detect metaphors by introducing domain-specific lexical features. |
| Outcome: | The proposed dataset includes 13,820 text-image pairs of advertisements with manual annotations of the occurrence of metaphors, domain categories, and sentiments metaphors convey. |
Distinguishing Address vs. Reference Mentions of Personal Names in Text (2023.findings-acl)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a core task in the NLP community . but not much work has been done to distinguish between addressing and referring to entities . |
| Approach: | They propose an automatic tagger that captures the address vs. reference distinction in English . they demonstrate how this distinction is important in NLP and computational social science applications . |
| Outcome: | The proposed tagger performs at 85% accuracy in distinguishing between address and reference in English . many modern Indo-European languages do not have such vocative case markers . |
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | LSTMs can capture syntactic rules in artificial languages, but it is unclear whether they are as capable in natural languages. |
| Approach: | They propose a causal account of structural properties as carried by paths across gates and neurons of a recurrent neural network that localizes and segments the concept into a set of gate or neuron-level paths. |
| Outcome: | The proposed model improves on a widely-studied multi-layer LSTM language model showing that it can learn subject-verb number agreement in English. |
Offensive Language and Hate Speech Detection for Danish (2020.lrec-1)
Copied to clipboard
| Challenge: | a growing number of social media platforms are detecting and dealing with offensive language . a recent study found that the best performing system for English is best for Danish . |
| Approach: | They propose automatic methods to detect offensive language on social media platforms . they use user-generated comments from various social media sites to find offensive language . |
| Outcome: | The proposed system performs best for both English and Danish language . it achieves a macro averaged F1-score of 0.74 and a best for Danish achieves 0.73 . |
GPT Perdetry Test: Generating new meanings for new words (2021.naacl-main)
Copied to clipboard
| Challenge: | We create a set of nonce words and prompt GPT-3 to generate their dictionary definitions. |
| Approach: | They create a set of nonce words and prompt GPT-3 to generate their dictionary definitions. |
| Outcome: | The proposed model can process new words and make them 'neologisms' . it can also adapt to and extend a changing vocabulary, the authors found . |
Distribution Aware Metrics for Conditional Natural Language Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing metrics for conditional natural language generation rely on pairwise comparisons between a single generated text and the best-matching reference. |
| Approach: | They propose a family of meta-metrics that build on existing pairwise distance functions to evaluate conditional natural language generation models. |
| Outcome: | The proposed method evaluates the ability of a model to generate text matching diversity in references in visual description and summarization. |
Does the Language Matter? Curriculum Learning over Neo-Latin Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | Curriculum Learning (CL) is emerging as a useful technique to reduce the cost of pre-training Large Language Models. |
| Approach: | They propose to organize training examples from the simplest to the most complex . they then test the approach to Italian and French to determine the complexity of examples . |
| Outcome: | The proposed method can be exported to other languages without adaptation. |
INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages (2025.acl-long)
Copied to clipboard
Hao Yu, Jesujoba Oluwadara Alabi, Andiswa Bukula, Jian Yun Zhuang, En-Shiun Annie Lee, Tadesse Kebede Guge, Israel Abebe Azime, Happy Buzaaba, Blessing Kudzaishe Sibanda, Godson Koffi Kalipe, Jonathan Mukiibi, Salomon Kabongo Kabenamualu, Mmasibidi Setaka, Lolwethu Ndolela, Nkiruka Odu, Rooweither Mabuya, Shamsuddeen Hassan Muhammad, Salomey Osei, Sokhar Samb, Dietrich Klakow, David Ifeoluwa Adelani
| Challenge: | Slot-filling and intent detection tasks are well-established tasks in Conversational AI, but current benchmarks for these tasks rely on evaluations of low-resource languages and translations from English benchmarks. |
| Approach: | They propose to use a multilingual, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains. |
| Outcome: | The proposed dataset compares multilingual transformer models and prompting large language models (LLMs) with the English language. |
Exploring Data Augmentation Strategies for Hate Speech Detection in Roman Urdu (2022.lrec-1)
Copied to clipboard
| Challenge: | a number of social media platforms are generating hateful content, a new study finds . augmentation techniques are needed to improve the performance of the models . |
| Approach: | They evaluate different data augmentation techniques for the improvement of hate speech detection in Roman Urdu. |
| Outcome: | The proposed techniques improve hate speech detection in Roman Urdu on two datasets. |
IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context (2024.naacl-long)
Copied to clipboard
Nihar Sahoo, Pranamya Kulkarni, Arif Ahmad, Tanu Goyal, Narjis Asad, Aparna Garimella, Pushpak Bhattacharyya
| Challenge: | Existing benchmark datasets focus on English language and the Western context, leaving a void for a reliable dataset that encapsulates India’s unique socio-cultural nuances. |
| Approach: | They propose to use CrowS-Pairs to create a benchmark dataset that captures and evaluates social biases in Large Language Models (LLMs). |
| Outcome: | The proposed dataset is available in English and Hindi and leverages LLMs ChatGPT and InstructGPT to augment the existing dataset with diverse societal biases and stereotypes prevalent in India. |
Translation-Enhanced Multilingual Text-to-Image Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models for text-to-image generation are mostly based on the English language due to the lack of annotated image-caption data in other languages. |
| Approach: | They propose to use a multilingual multi-modal encoder to bootstrap mTTI systems that can be translated into other languages. |
| Outcome: | The proposed approach mitigates the language gap and improves on standard mTTI datasets. |
Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches (2020.coling-main)
Copied to clipboard
Sidney Evaldo Leal, João Marcos Munguba Vieira, Erica dos Santos Rodrigues, Elisângela Nogueira Teixeira, Sandra Aluísio
| Challenge: | Sentence complexity assessment is a relatively new task in Natural Language Processing. |
| Approach: | They propose to use Brazilian Portuguese to evaluate sentences with linguistic features to improve readability. |
| Outcome: | The proposed model reaches the state-of-the-art for Brazilian Portuguese with 97.8% accuracy with linguistic features. |
The Plagiarism Singularity Conjecture (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are being used to generate content at an unprecedented scale, raising concerns over their misuse and saturation of the content space with artificially generated material. |
| Approach: | They propose to use large language models to generate text that looks indistinguishable from that written by humans. |
| Outcome: | The proposed model can generate 10-30 sentences to breach the plagiarism limit, the authors estimate . |
Privacy at Scale: Introducing the PrivaSeer Corpus of Web Privacy Policies (2021.acl-long)
Copied to clipboard
| Challenge: | Existing tools to interpret privacy policies have been used to understand them but there is a lack of large privacy policy corpora to simplify the process. |
| Approach: | They propose to use a corpus of 1,005,380 English language privacy policies collected from the web to create semi-supervised and unsupervised models to interpret and simplify privacy policies. |
| Outcome: | The proposed model outperforms all other publicly available privacy policy corpora and is ten times larger than the next largest public collection of privacy policies combined. |
Perturbation Sensitivity Analysis to Detect Unintended Model Biases (D19-1)
Copied to clipboard
| Challenge: | Recent research shows that data-driven NLP models may inadvertently capture, reflect and sometimes amplify various social biases present in the language data they are trained on. |
| Approach: | They propose a generic evaluation framework that detects unintended model biases related to named entities and requires no new annotations or corpora. |
| Outcome: | The proposed framework detects unintended model biases related to named entities and requires no new annotations or corpora. |
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks for assessing distinct meanings of words are tied to sense inventories, restricting their usage to knowledge-based representation techniques. |
| Approach: | They propose a multilingual benchmark that models distinct meanings of words in English . they use a binary disambiguation task with gold standards in 12 new languages . |
| Outcome: | The proposed model can model distinct meanings of words in English even when no tagged instances are available for a target language. |
BRATECA (Brazilian Tertiary Care Dataset): a Clinical Information Dataset for the Portuguese Language (2022.lrec-1)
Copied to clipboard
Bernardo Consoli, Henrique D. P. dos Santos, Ana Helena D. P. S. Ulbrich, Renata Vieira, Rafael H. Bordini
| Challenge: | Existing clinical datasets are in the English language and were collected in anglophone countries. |
| Approach: | They propose to use a Brazilian clinical dataset with over 2.5 million free-text clinical notes alongside data pertaining to patient information, prescription information, and exam results. |
| Outcome: | The Brazilian Clinical Dataset contains over 70,000 admissions from 10 hospitals in two Brazilian states. |
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning (2024.acl-long)
Copied to clipboard
Shivalika Singh, Freddie Vargus, Daniel D’souza, Börje Karlsson, Abinaya Mahendiran, Wei-Yin Ko, Herumb Shandilya, Jay Patel, Deividas Mataciunas, Laura O’Mahony, Mike Zhang, Ramith Hettiarachchi, Joseph Wilson, Marina Machado, Luisa Moura, Dominik Krzemiński, Hakimeh Fadaei, Irem Ergun, Ifeoma Okoh, Aisha Alaagib, Oshan Mudannayake, Zaid Alyafeai, Vu Chien, Sebastian Ruder, Surya Guthikonda, Emad Alghamdi, Sebastian Gehrmann, Niklas Muennighoff, Max Bartolo, Julia Kreutzer, Ahmet Üstün, Marzieh Fadaee, Sara Hooker
| Challenge: | Existing datasets in the English language are mostly in the realm of instruction fine-tuning . aya dataset, the Aya Collection, and the AYa Evaluation Suite are key resources . |
| Approach: | They aim to build a human-curated instruction-following dataset spanning 65 languages . they work with fluent speakers of languages from around the world to collect natural instances of instructions and completions . |
| Outcome: | The goal is to build a human-curated instruction-following dataset spanning 65 languages. |
EUROPA: A Legal Multilingual Keyphrase Generation Dataset (2024.acl-long)
Copied to clipboard
| Challenge: | Keyphrases are short phrases that describe a text and have been used for many applications. |
| Approach: | They present a dataset for multilingual keyphrase generation in the legal domain . it is derived from legal judgments from the Court of Justice of the European Union . they run multilingual models on the corpus and analyze the results . |
| Outcome: | The proposed dataset shows that it is better than existing models and can capture larger input context. |
Language Proficiency Scoring (2020.lrec-1)
Copied to clipboard
| Challenge: | a new paper evaluates and extends the results of an automated proficiency classification system for different languages. |
| Approach: | They propose to extend an automated essay scoring system proposed by CEFR . they compare results with those from previous paper and add a new corpus for english . |
| Outcome: | The proposed approach does not scale well with the added English corpus. |
GreekBART: The First Pretrained Greek Sequence-to-Sequence Model (2024.lrec-main)
Copied to clipboard
Iakovos Evdaimon, Hadi Abdine, Christos Xypolopoulos, Stamatis Outsios, Michalis Vazirgiannis, Giorgos Stamou
| Challenge: | Transfer learning has revolutionized the fields of Computer Vision and Natural Language Processing. |
| Approach: | They introduce a new language model, GreekBART, that is based on a BART-base architecture. |
| Outcome: | The proposed model outperforms BERT, GPT and other transformer-based models on discriminative tasks. |
BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset (2022.lrec-1)
Copied to clipboard
| Challenge: | BAN-Cap dataset is based on the widely used Flickr8k dataset, which is used to collect captions of images from qualified annotators. |
| Approach: | They propose to use a dataset to collect Bangla captions from qualified annotators and to evaluate the models for the task. |
| Outcome: | The proposed model outperforms state-of-the-art models for Bangla captioning and English-Bangla translation. |
A Simple Yet Effective Corpus Construction Method for Chinese Sentence Compression (2022.lrec-1)
Copied to clipboard
| Challenge: | Deletion-based sentence compression has made significant progress in the english language . however, there is a lack of large-scale and high-quality parallel corpus for the Chinese language to train an efficient system. |
| Approach: | They propose to construct a Chinese corpus with 151k pairs of sentences and train extractive and generative neural compression models on the constructed corpus. |
| Outcome: | The proposed method generates high-quality compressed sentences on automatic and human evaluation metrics compared with baselines. |
Chinese Opinion Role Labeling with Corpus Translation: A Pivot Study (2021.emnlp-main)
Copied to clipboard
| Challenge: | Unlike most of the previous work focusing on the English language, this paper focuses on the Chinese ORL task. |
| Approach: | They propose to use a standard English MPQA dataset to construct a Chinese ORL dataset and investigate the effectiveness of cross-lingual transfer methods. |
| Outcome: | The proposed method is able to detect and improve the performance of the proposed method in Chinese. |
Unveiling the Essence of Poetry: Introducing a Comprehensive Dataset and Benchmark for Poem Summarization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Summarization of poetry is a challenging task as it can be easily lost if only the literal meaning is considered. |
| Approach: | They propose to use poetry as a model to summarize poetry and provide a dataset to evaluate their creative language interpretation capacity. |
| Outcome: | The proposed dataset consisting of 3011 samples and its corresponding summarized interpretation in the English language provides an opportunity to evaluate the creative language interpretation capacity of the proposed models. |
M2SA: Multimodal and Multilingual Model for Sentiment Analysis of Tweets (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on sentiment analysis of tweets focus on the English language . however, there is still a challenge of processing lower-resourced languages . |
| Approach: | They transform tweet sentiment dataset into a multimodal format through a straightforward curation process. |
| Outcome: | The proposed approach performs exceptionally well in unimodal and multimodal configurations. |
A Culturally-diverse Multilingual Multimodal Video Benchmark & Model (2025.emnlp-main)
Copied to clipboard
Bhuiyan Sanjid Shafique, Ashmal Vayani, Muhammad Maaz, Hanoona Abdul Rasheed, Dinura Dissanayake, Mohammed Irfan Kurpath, Yahya Hmaiti, Go Inoue, Jean Lahoud, Md. Safirur Rashid, Shadid Intisar Quasem, Maheen Fatima, Franco Vidal, Mykola Maslych, Ketan Pravin More, Sanoojan Baliah, Hasindri Watawana, Yuhao Li, Fabian Farestam, Leon Schaller, Roman Tymtsiv, Simon Weber, Hisham Cholakkal, Ivan Laptev, Shin’ichi Satoh, Michael Felsberg, Mubarak Shah, Salman Khan, Fahad Shahbaz Khan
| Challenge: | Large multimodal models have gained attention for their effectiveness to understand and generate descriptions of visual content. |
| Approach: | They propose a multilingual Video LMM benchmark to evaluate video LMMs across 14 languages . they also introduce a machine translated multilingual video training set . |
| Outcome: | The proposed video LMM benchmark is designed to evaluate video Lmms across 14 languages including Arabic, Bengali, Chinese, English, French, German, Hindi, Japanese, Russian, Sinhala, Spanish, Swedish, Tamil, and Urdu. |
Multilingual Coreference Resolution in Low-resource South Asian Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing coreference resolution models for South Asian languages are limited . a a sanity check for the prediction of translations is required to ensure accuracy of the model, authors say . |
| Approach: | They evaluate an end-to-end coreference resolution model on a Hindi golden set . they use translation and word-alignment tools to translate a translated dataset into 31 languages . |
| Outcome: | The proposed model scored 64 and 68 on a Hindi golden set. |
Tell, Don’t Show: Leveraging Language Models’ Abstractive Retellings to Model Literary Themes (2025.findings-acl)
Copied to clipboard
| Challenge: | Literature challenges traditional bag-of-words approaches for topic modeling because narrative language focuses on immersive sensory details instead of abstractive description or exposition. |
| Approach: | They propose a topic modeling approach that prompts generative language models to *tell* what passages *show*, thereby translating narratives’ surface forms into higher-level concepts and themes. |
| Outcome: | The proposed model can translate narratives’ surface forms into higher-level concepts and themes than by running LDA alone or directly asking LMs to list topics. |
Release of Pre-Trained Models for the Japanese Language (2024.lrec-main)
Copied to clipboard
Kei Sawada, Tianyu Zhao, Makoto Shing, Kentaro Mitsui, Akio Kaga, Yukiya Hono, Toshiaki Wakatsuki, Koh Mitsuda
| Challenge: | democratization of AI aims to create a world where everyone can use AI . pre-trained models with high performance in Japanese are lagging in non-English-speaking communities . |
| Approach: | et al. released large-scale pre-trained models trained on large-data to improve access to AI . authors say the models are more accurate and more accurate than those trained in the English language . e-mail protected: email protected. |
| Outcome: | a new study shows that pre-trained models specialized for Japanese can achieve high performance in Japanese tasks. |
Mapping the Podcast Ecosystem with the Structured Podcast Research Corpus (2025.acl-long)
Copied to clipboard
| Challenge: | a dataset of over 1.1M podcast transcripts is largely comprehensive of all English language podcasts available through public RSS feeds from May and June of 2020. |
| Approach: | They propose to build a large-scale open dataset of podcast transcripts that includes metadata, speaker roles, audio features and speaker turns for a subset of 370K episodes. |
| Outcome: | The proposed dataset is largely comprehensive of all English language podcasts available through public RSS feeds from May and June of 2020. |
ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding (2025.acl-long)
Copied to clipboard
| Challenge: | 3D visual grounding models localize entities in a scene referred to by natural language text . recent studies focused on LLM-based scaling of 3DVG datasets, but these do not capture the full range of potential prompts which could be specified in the English language. |
| Approach: | They propose a framework for linguistically analyzing 3DVG prompts and introduce a diagnostic dataset for evaluating 3D visual grounding methods against a diverse set of language patterns. |
| Outcome: | The proposed framework scales up and tests against a representative set of prompts in the english language. |