SUPERVISED MODELS

TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network (2021.emnlp-main)

Challenge:	a study of neural language models shows that syntactic probes do not properly isolate syntax.
Approach:	They show that syntactic probes do not properly isolate syntax . they train two probes trained on normal data and find they perform worse .
Outcome:	The proposed method outperforms the baseline models on the most popular models, but their lead is reduced by 53%.

Copied to clipboard

Zheng Fang, Yanan Cao, Tai Li, Ruipeng Jia, Fang Fang, Yanmin Shang, Yuhai Lu

kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning (2024.naacl-long)

Challenge:	Existing methods to label data and identify entities require large amounts of manually annotated texts for training supervised models.
Approach:	They propose a dictionary extension method which extracts new entities through the type expanded model.
Outcome:	The proposed method outperforms state-of-the-art supervised systems on different types of datasets and surpasses supervised models.

Copied to clipboard

Wenting Zhao, Ye Liu, Yao Wan, Yibo Wang, Qingyang Wu, Zhongfen Deng, Jiangshu Du, Shuaiqi Liu, Yunlong Xu, Philip Yu

Cross-lingual Structure Transfer for Relation and Event Extraction (D19-1)

Challenge:	Recent advances in task-oriented parsing involve formulating the task as a sequence-to-sequence problem, relying on a wealth of labeled data.
Approach:	They propose a task-oriented parsing framework that integrates nearest-neighbor learning with a nearest-nearest approach.
Outcome:	The proposed model can be used to synthesize computer programs based on a natural-language prompt without additional data or specialized prompts.

Copied to clipboard

Ananya Subburathinam, Di Lu, Heng Ji, Jonathan May, Shih-Fu Chang, Avirup Sil, Clare Voss

Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification (2024.acl-long)

Challenge:	Existing approaches to identify complex semantic structures are difficult to train from under-annotated sources.
Approach:	They exploit relation- and event-relevant language-universal features to train relation or event extractors from source annotations and apply them to target languages.
Outcome:	The proposed approach achieves comparable performance to state-of-the-art models trained on 3,000 manually annotated mentions.

Copied to clipboard

Yibo Hu, Erick Skorupa Parolin, Latifur Khan, Patrick Brandt, Javier Osorio, Vito D’Orazio

Generate, Annotate, and Learn: NLP with Synthetic Text (2022.tacl-1)

Challenge:	Existing annotation codebook is labor-intensive for coding events from large datasets.
Approach:	They propose to use existing annotation codebook to classify political relations without extensive annotations.
Outcome:	The proposed methods outperform dictionary-based methods and the existing ontology annotation codebook and improve interpretability and efficiency.

Copied to clipboard

Xuanli He, Islam Nassar, Jamie Kiros, Gholamreza Haffari, Mohammad Norouzi

A Hybrid Approach to Aspect Based Sentiment Analysis Using Transfer Learning (2024.lrec-main)

Challenge:	Existing methods to generate unlabeled text are difficult to find.
Approach:	They propose a general framework called "generate, annotate, and learn" to take advantage of synthetic text within knowledge distillation, self-training, and few-shot learning applications.
Outcome:	The proposed framework achieves state-of-the-art knowledge distillation results for 6-layer transformers on the GLUE leaderboard.

Copied to clipboard

Gaurav Negi, Rajdeep Sarkar, Omnia Zayed, Paul Buitelaar

Unsupervised Subtitle Segmentation with Masked Language Models (2023.acl-short)

Challenge:	Aspect-Based Sentiment Analysis (ABSA) aims to identify terms or multiword expressions (MWEs) on which sentiments are expressed and the sentiment polarities associated with them.
Approach:	They propose a hybrid approach to Aspect-Based Sentiment Analysis using transfer learning . they exploit the strengths of large language models and traditional syntactic dependencies .
Outcome:	The proposed method exploits the strengths of large language models and traditional syntactic dependencies.

Copied to clipboard

David Ponce, Thierry Etchegoyhen, Victor Ruiz

StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing (P18-1)

Challenge:	Existing methods to improve subtitle segmentation are based on character counting and linguistically correct segmentation.
Approach:	They propose a method where subtitle breaks are predicted according to likelihood of punctuation . their approach is highly portable across languages and domains .
Outcome:	The proposed method obtained competitive results in terms of segmentation accuracy across metrics while also fully preserving the original text and complying with length constraints.

Copied to clipboard

Pengcheng Yin, Chunting Zhou, Junxian He, Graham Neubig

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling (2026.findings-acl)

Challenge:	Semantic parsing is the task of transducing natural language (NL) utterances into formal meaning representations (MRs), commonly represented as tree structures.
Approach:	They propose a variational auto-encoding model for semi-supervised semantic parsing which learns from limited amounts of parallel data and readily-available unlabeled NL utterances.
Outcome:	Experiments on ATIS domain and Python show that with extra unlabeled data, StructVAE outperforms strong supervised models.

Copied to clipboard

Shuliang Liu, Zhipeng Xu, Zhenghao Liu, Yukun Yan, Minghe Yu, Yu Gu, Chong Chen, Huiyuan Xie, Ge Yu

Unsupervised FAQ Retrieval with Question Generation and BERT (2020.acl-main)

Challenge:	Large Language Models (LLMs) are used as automatic evaluators to provide accurate and reliable assessments.
Approach:	They propose a framework that integrates LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism.
Outcome:	The proposed framework outperforms supervised models trained on annotated judgment data while requiring no human-labeled annotations.

Copied to clipboard

Yosi Mass, Boaz Carmeli, Haggai Roitman, David Konopnicki

A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling (P18-1)

Challenge:	Frequently Asked Questions (FAQ) retrieval requires labeled datasets for training neural models.
Approach:	They propose to exploit FAQ pairs to train two BERT models that match user queries to FAQ answers and questions.
Outcome:	The proposed model outperforms supervised models on existing datasets and is on par with existing dataset.

Copied to clipboard

Ying Lin, Shengqi Yang, Veselin Stoyanov, Heng Ji

Open-Domain Event Detection using Distant Supervision (C18-1)

Challenge:	Existing studies have shown that multi-task learning can boost the performance of related tasks such as MT and abstractive text summarization.
Approach:	They propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling.
Outcome:	The proposed architecture achieves 4.3%-50.5% absolute gains compared to mono-lingual model . the proposed model is particularly effective in low-resource settings .

Copied to clipboard

Jun Araki, Teruko Mitamura

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations (2022.emnlp-main)

Challenge:	Existing work on restricted domains and event annotation has limited coverage of events.
Approach:	They propose a distant supervision method that generates high-quality training data . they use a manually annotated corpus as a model to investigate events in various domains .
Outcome:	The proposed method outperforms supervised models in a manually annotated event corpus despite no direct supervision .

Copied to clipboard

Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi

Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs (2021.eacl-main)

Challenge:	Pre-trained language models struggle with consistent reasoning, and prompting methods are often noisy and inconsistent.
Approach:	They propose a few-shot inference method inspired by the Socratic way of conversation that generates a tree of explanations that bear logical relations between each other and frames it as a satisfiability problem.
Outcome:	The proposed method achieves 20% better accuracy than state-of-the-art prompting methods and performs competitively with supervised models.

Copied to clipboard

Kuan-Hao Huang, Kai-Wei Chang

Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation (2021.eacl-main)

Challenge:	Paraphrase generation requires many annotated paraphrase pairs, which are expensive to obtain.
Approach:	They propose a model that learns to disentangle the semantics and syntax of a sentence from unannotated texts.
Outcome:	The proposed model learns to disentangle the semantics and syntax of a sentence from a collection of unannotated texts.

Copied to clipboard

Ji Ma, Ivan Korotkov, Yinfei Yang, Keith Hall, Ryan McDonald

Knowledge-Augmented Language Model and Its Application to Unsupervised Named-Entity Recognition (N19-1)

Challenge:	Recent advances in neural retrieval have led to advancements on document, passage and knowledge-base benchmarks.
Approach:	They propose an approach to zero-shot learning for passage retrieval that uses synthetic question generation to close this gap.
Outcome:	The proposed approach can exceed term-based techniques on document retrieval benchmarks by using domain-targeted synthetic question generation.

Copied to clipboard

Angli Liu, Jingfei Du, Veselin Stoyanov

A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal (2020.acl-main)

Challenge:	Current language models are unable to efficiently model entity names observed in text providing insufficient context.
Approach:	They propose to augment a traditional model with an external knowledge base to model entity names observed in text.
Outcome:	The proposed model improves on a Named Entity Recognition (NER) task by requiring no additional information such as named entity tags.

Copied to clipboard

Demian Gholipour Ghalandari, Chris Hokamp, Nghia The Pham, John Glover, Georgiana Ifrim

“Wikily” Supervised Neural Translation Tailored to Cross-Lingual Tasks (2021.emnlp-main)

Challenge:	Multidocument summarization (MDS) aims to compress large document collections into short summaries.
Approach:	They propose a large-scale multidocument summarization dataset that is large both in total number of document clusters and in the size of individual clusters.
Outcome:	The proposed dataset is large both in the total number of document clusters and in the size of individual clusters.

Copied to clipboard

Mohammad Sadegh Rasooli, Chris Callison-Burch, Derry Tanti Wijaya

Research Replication Prediction Using Weakly Supervised Learning (2020.findings-emnlp)

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.

Copied to clipboard

Tianyi Luo, Xingyu Li, Hainan Wang, Yang Liu

Detecting Narrative Elements in Informational Text (2022.findings-naacl)

Challenge:	Existing methods to predict scientific claims’ replicability use only hand-extracted statistics features without utilizing research papers’ text information.
Approach:	They propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets.
Outcome:	The proposed methods achieve an accuracy of 75.76% over real-world datasets.

Copied to clipboard

Effi Levi, Guy Mor, Tamir Sheafer, Shaul Shenhav

Linguistic Theories

Challenge:	Recent work has focused on identifying narrative elements in personal stories texts, but this paper focuses on informational texts.
Approach:	They propose a novel NLP task for detecting narrative elements in raw text by adapting elements from the oral narrative theory of Labov and Waletzky and adding a new narrative element of their own.
Outcome:	The proposed scheme achieves an average F1 score of 0.77 and is better suited for informational texts than the oral narrative theory.

Improving Unsupervised Extractive Summarization with Facet-Aware Modeling (2021.findings-acl)

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li

Neural Storyline Extraction Model for Storyline Generation from News Articles (N18-1)

Challenge:	Existing extractive summarization methods tend to select sentences within the same facet, which leads to facet bias.
Approach:	They propose a facet-aware centrality-based ranking model that gives a weight to the sentence centrality score.
Outcome:	The proposed method outperforms baseline models on a wide range of summarization tasks and performs comparably to other models.

Copied to clipboard

Deyu Zhou, Linsen Guo, Yulan He

Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources (L18-1)

Challenge:	Existing approaches to storyline generation are domain dependent and cannot deal with unseen event types.
Approach:	They propose a neural network-based approach to extract structured representations and evolution patterns of storylines without using annotated data.
Outcome:	The proposed model outperforms state-of-the-art approaches on accuracy and efficiency on three news corpora and it is based on supervised models.

Copied to clipboard

Stefano Melacci, Achille Globo, Leonardo Rigutini

Lin: Unsupervised Extraction of Tasks from Textual Communication (2020.coling-main)

Challenge:	Existing supervised models for Word Sense Disambiguation (WSD) are limited to knowledge-based approaches.
Approach:	They propose to use WordNet and WordNet Domains to enhance supervised WSD models by introducing semantic features into the classifiers and using the SLR structure to augment training data.
Outcome:	The proposed model improves the state-of-the-art in Word Sense Disambiguation (WSD) The proposed approach is compared with the state of the art in the most popular benchmarks.

Copied to clipboard

Parth Diwanji, Hui Guo, Munindar Singh, Anup Kalia

Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models (2022.naacl-main)

Challenge:	Identifying tasks from emails and chats is a hallmark of collaborative communication . state-of-the-art approaches for task identification rely on large annotated datasets .
Approach:	They propose an unsupervised approach to identifying tasks that leverages dependency parsing and VerbNet.
Outcome:	The proposed approach yields comparable or more accurate results than supervised models on unseen domains.

Copied to clipboard

Patrick Huber, Giuseppe Carenini

An Analysis of Annotated Corpora for Emotion Classification in Text (C18-1)

Challenge:	Existing approaches to pre-training/fine-tuning are focusing on the alignment of pre-trained and fine-tuned PLMs with large-scale discourse structures.
Approach:	They propose a novel approach to infer discourse information for arbitrarily long documents using supervised, distantly supervised and simple baselines.
Outcome:	The proposed approach shows that the captured discourse information is local and general, even across fine-tuning tasks.

Copied to clipboard

Laura-Ana-Maria Bostan, Roman Klinger

Modeling Framing in Immigration Discourse on Social Media (2021.naacl-main)

Challenge:	Several datasets have been annotated and published for classification of emotions.
Approach:	They aggregated emotion corpora in a common file format with a shared annotation schema . they perform cross-corpus classification experiments to gain insight and a better understanding of differences .
Outcome:	The proposed model can be trained on a subset of corpora, but not on all corporata.

Copied to clipboard

Julia Mendelsohn, Ceren Budak, David Jurgens

Challenge:	Using a dataset of immigration-related tweets, we examine how ordinary people on social media frame political issues.
Approach:	They propose to use a dataset of immigration-related tweets labeled for multiple framing typologies from political communication theory to analyze framers.
Outcome:	The proposed model enables comparisons between different types of frames on social media and a dataset of immigration-related tweets.

GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives (2024.naacl-long)

Copied to clipboard

Vinodkumar Prabhakaran, Christopher Homan, Lora Aroyo, Aida Mostafazadeh Davani, Alicia Parrish, Alex Taylor, Mark Diaz, Ding Wang, Gregory Serapio-García

Challenge:	Recent work shows that ignoring rater subjectivity is problematic within specific tasks and for specific subgroups.
Approach:	They propose a disagreement analysis framework to measure group association in perspectives among different rater subgroups.
Outcome:	The proposed framework reveals specific rater groups that have significantly different perspectives than others on certain tasks and helps identify demographic axes that are crucial to consider in specific task contexts.

Global Constraints with Prompting for Zero-Shot Event Argument Classification (2023.findings-eacl)

Copied to clipboard

Zizheng Lin, Hongming Zhang, Yangqiu Song

Code4Struct: Code Generation for Few-Shot Event Structure Prediction (2023.acl-long)

Challenge:	Existing zero-shot trigger extraction models require annotations, which is not practical for open-domain applications.
Approach:	They propose to use global constraints with prompting to tackle event argument classification without annotation and task-specific training.
Outcome:	The proposed model outperforms the best zero-shot baselines by 12.5% and 10.9% F1 on ACE and ERE with given argument spans and by 4.3% and 3.3% F1 without given argument spas.

Copied to clipboard

Xingyao Wang, Sha Li, Heng Ji

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking (P19-1)

Challenge:	Large Language Models (LLMs) trained on a mixture of text and code have demonstrated impressive capability in translating natural language (NL) into structured code.
Approach:	They propose to use programming language (PL) inheritance and type annotations to translate text into code to tackle structured prediction tasks.
Outcome:	The proposed model outperforms existing models on 20-shot data by 29.5% absolute F1.

Copied to clipboard

Masaru Isonuma, Junichiro Mori, Ichiro Sakata

Semi-Supervised Sequence Modeling with Cross-View Training (D18-1)

Challenge:	Currently, unsupervised summarization is widely used for product reviews on E-commerce websites.
Approach:	They propose an unsupervised model that learns the latent discourse tree without an external parser and generates a concise summary.
Outcome:	The proposed model outperforms other unsupervised approaches for relatively long reviews and is competitive with or better than supervised models.

Copied to clipboard

Kevin Clark, Minh-Thang Luong, Christopher D. Manning, Quoc Le

Uncovering Temporal Framing in the News (2026.acl-long)

Challenge:	Unsupervised representation learning algorithms such as word2vec and ELMo only learn from task-specific labeled data during the main training phase.
Approach:	They propose a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data.
Outcome:	The proposed algorithm improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data.

Copied to clipboard

Tarek Mahmoud, Veronika Solopova, Premtim Sahitaj, Ariana Sahitaj, Max Upravitelev, Mervat Abassy, Hana Fatima Shaikh, Neda Foroutan, Vera Schmitt, Preslav Nakov

Contrastive Learning of Sentence Embeddings from Scratch (2023.emnlp-main)

Challenge:	Temporal language is used to structure meaning rather than report chronology in news discourse . a recent study focused on temporal expression extraction and temporal reasoning .
Approach:	They propose a taxonomy of eight temporal frames grounded in prior work on time and framing . they analyze frame prevalence, co-occurrence patterns, and lexical cues from a news corpus .
Outcome:	The proposed taxonomy outperforms zero-shot models at the sentence level . it shows that temporal framing is learnable at the sentences level compared to other methods .

Copied to clipboard

Junlei Zhang, Zhenzhong Lan, Junxian He

GPT-NER: Named Entity Recognition via Large Language Models (2025.findings-naacl)

Challenge:	Existing approaches to learn sentence embeddings with unlabeled data are limited due to copyright restrictions, data distribution issues, and messy formats.
Approach:	They propose a contrastive learning framework that trains sentence embeddings with synthetic data.
Outcome:	The proposed framework produces positive and negative annotations given unlabeled sentences and generates sentences along with their corresponding annotations from scratch.

Copied to clipboard

Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, Guoyin Wang, Chen Guo

Improving Passage Retrieval with Zero-Shot Question Generation (2022.emnlp-main)

Challenge:	Large-scale language models (LLMs) have shown impressive ability for in-context learning with limited training data.
Approach:	They propose a novel sequence labeling task that transforms a sequence labeled as a text-generation task into a self-verification task that LLMs can adapt to.
Outcome:	The proposed model performs better on NER than supervised models on a variety of tasks . the proposed model can be easily adapted by LLMs to generate a text sequence .

Copied to clipboard

Devendra Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan, Wen-tau Yih, Joelle Pineau, Luke Zettlemoyer

Can We Identify Stance without Target Arguments? A Study for Rumour Stance Classification (2024.lrec-main)

Challenge:	Existing re-ranking methods for open-domain question answering are not domain- or task-specific.
Approach:	They propose a simple and effective re-ranking method for improving passage retrieval in open-domain question answering.
Outcome:	The proposed method outperforms strong supervised models on open-domain questions and triviaQA datasets on top-1000 passages.

Copied to clipboard

Yue Li, Carolina Scarton

Text Classification

Challenge:	Existing target-aware models underperform in cases where the context of the target is crucial.
Approach:	They propose a framework to enhance reasoning with the targets and propose 'target-aware' models without awareness of the target.
Outcome:	The proposed framework achieves state-of-the-art on two benchmark datasets.

Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articles (2024.findings-emnlp)

Copied to clipboard

Filip Trhlík, Pontus Stenetorp

Hallucination Detection for Grounded Instruction Generation (2023.findings-emnlp)

Challenge:	Existing studies focus on LLMs undertaking political questionnaires, which offers only limited insights into their biases and operational nuances.
Approach:	They propose to use a curated dataset to generate 56,700 synthetic articles using nine LLMs.
Outcome:	The proposed model can detect political biases using supervised models and LLMs.

Copied to clipboard

Lingjun Zhao, Khanh Nguyen, Hal Daumé III

Reasoning

Challenge:	Existing models for generating instructions for navigation generate references to objects or actions that are inconsistent with what a human follower would perform or encounter along the path.
Approach:	They propose a weakly supervised approach that detects hallucinated references by using a pre-trained vision-language model.
Outcome:	The proposed model outperforms baseline models and supervised models on generating navigation instructions.

Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging (D18-1)

Copied to clipboard

Tao Gui, Qi Zhang, Jingjing Gong, Minlong Peng, Di Liang, Keyu Ding, Xuanjing Huang

Designing and Interpreting Probes with Control Tasks (D19-1)

Challenge:	Existing POS tagging methods for Twitter use labeled newswire text . however, Twitter users tend to mimic formal media expressions and develop linguistically informal styles.
Approach:	They propose to use newswire text to learn POS tagging for Twitter while twitter users are developing linguistically informal styles.
Outcome:	The proposed method achieves better performance than state-of-the-art methods on three different datasets.

Copied to clipboard

John Hewitt, Percy Liang

Answer Consolidation: Formulation and Benchmarking (2022.naacl-main)

Challenge:	Existing studies on supervised models to predict properties from representations have shown high accuracy on a range of linguistic tasks.
Approach:	They propose control tasks which associate word types with random outputs to complement linguistic tasks by construction . they find that popular probes on ELMo representations are not selective .
Outcome:	The proposed tasks associate word types with random outputs to complement linguistic tasks.

Copied to clipboard

Wenxuan Zhou, Qiang Ning, Heba Elfardy, Kevin Small, Muhao Chen

Natural Language Interfaces

Challenge:	Current question answering systems assume each question to have one correct answer.
Approach:	They propose a problem where answers are partitioned into multiple groups . they construct a comprehensive and non-redundant set of answers by picking one answer from each group .
Outcome:	The proposed model performs better than previous models, but it needs further improvements.

Few-Shot Learning for Opinion Summarization (2020.emnlp-main)

Copied to clipboard

Arthur Bražinskas, Mirella Lapata, Ivan Titov

On Learning Text Style Transfer with Direct Rewards (2021.naacl-main)

Challenge:	a recent study shows that abstractive summarization models fail to capture their essential properties due to the high cost of summary production.
Approach:	They propose a few-shot framework for abstractive opinion summarization that bootstraps the output of an unsupervised model.
Outcome:	The proposed framework outperforms extractive and abstractive methods on Amazon and Yelp datasets.

Copied to clipboard

Yixin Liu, Graham Neubig, John Wieting

NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints (2021.naacl-main)

Challenge:	Existing methods for text style transfer lack parallel corpora, which makes it impossible to train supervised models.
Approach:	They propose to use semantic similarity metrics to explicitly assess the preservation of content between system outputs and inputs.
Outcome:	The proposed methods provide significant gains in automatic and human evaluation over strong baselines.

Copied to clipboard

Ximing Lu, Peter West, Rowan Zellers, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling (2023.emnlp-main)

Challenge:	Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text.
Approach:	They propose an algorithm that enables neural language models to generate fluent text while satisfying complex lexical constraints.
Outcome:	The proposed algorithm outperforms existing methods on four benchmarks and shows that it handles any set of lexical constraints expressible under predicate logic while its asymptotic runtime is equivalent to conventional beam search.

Copied to clipboard

Hai Yu, Chong Deng, Qinglin Zhang, Jiaqing Liu, Qian Chen, Wen Wang

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts (2020.emnlp-main)

Challenge:	Recent supervised neural models have greatly promoted the development of topic segmentation, but the deeper relationship between coherence and topic segmenting is underexplored.
Approach:	They propose to use topic-aware Sentence Structure Prediction and Contrastive Semantic Similarity Learning to capture coherence from logical structure and semantic similarity perspectives to further improve topic segmentation performance.
Outcome:	The proposed approach outperforms state-of-the-art methods on WIKI-727K and achieves an average relative reduction of 4.3% on Pk on WikiSection.

Copied to clipboard

Taylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace, Sameer Singh

ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension (2022.acl-long)

Challenge:	Pretrained language models have been successful when finetuned to downstream tasks . however, it is difficult to determine whether the knowledge that finetuning LMs contain is learned during the pretraining or the finetailing process.
Approach:	They propose a method to create prompts for a diverse set of tasks using a gradient-guided search.
Outcome:	The proposed method performs sentiment analysis and natural language inference without additional parameters and finetuning.

Copied to clipboard

Sanjay Subramanian, William Merrill, Trevor Darrell, Matt Gardner, Sameer Singh, Anna Rohrbach

Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models (2020.emnlp-main)

Challenge:	Visual referring expression comprehension (ReC) models can be trained for a domain, but it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC.
Approach:	They propose a method that repurposes CLIP, a state-of-the-art large-scale model, for training a referring expression comprehension model for a new visual domain.
Outcome:	The proposed model reduces the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on ReFGTA (video game imagery), and its relative improvement over supervised ReC models is 8%.

Copied to clipboard

Ethan Wilcox, Peng Qian, Richard Futrell, Ryosuke Kohita, Roger Levy, Miguel Ballesteros

A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization (2025.naacl-long)

Challenge:	Existing studies have not investigated the relationship between a token's frequency in the training corpus and syntactic properties models learn about it.
Approach:	They develop controlled experiments that probe models’ syntactic nominal number and verbal argument structure generalizations for tokens seen as few as two times during training.
Outcome:	The proposed models can make syntactic generalizations for tokens seen as few as two times during training and transfer them to transformed contexts.

Copied to clipboard

Haoxin Liu, Chenghao Liu, B. Aditya Prakash

Reasoning

Challenge:	Large language models (LLMs) have demonstrated powerful reasoning abilities across multiple domains, but have been underexplored for time-series reasoning (TsR)
Approach:	They propose a prompt-based solution for evaluating large language models’ TsR performance.
Outcome:	The proposed solution improves performance and costs by 140% and reduces costs by 99%.

Offensive language detection in Hebrew: can other languages help? (2022.lrec-1)

Copied to clipboard

Marina Litvak, Natalia Vanetik, Chaya Liebeskind, Omar Hmdia, Rizek Abu Madeghem

Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs (2022.naacl-main)

Challenge:	Various approaches for offensive language detection have been applied for this task . contamination of social networks with offensive content is a new reality affecting almost all of us .
Approach:	They propose to use multiple supervised models and text representations to detect offensive language in three languages, including two Semitic languages.
Outcome:	The proposed model can detect offensive content in two Semitic languages, including Hebrew and Arabic, and it is able to perform cross-lingual and multilingual learning.

Copied to clipboard

Ghazi Felhi, Joseph Le Roux, Djamé Seddah

Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition (2021.acl-long)

Challenge:	Existing models for text generation do not need syntactic information such as constituency parses or semantic information such a paraphrase pairs.
Approach:	They propose a generative model which exhibits disentangled latent representations of syntax and semantics by using Attention in its decoder.
Outcome:	The proposed model outperforms supervised models on syntax/semantics transfer and shows that it can read latent variables with keys and values.

Copied to clipboard

Xin Zhang, Guangwei Xu, Yueheng Sun, Meishan Zhang, Pengjun Xie

Neural Disambiguation of Lemma and Part of Speech in Morphologically Rich Languages (2020.lrec-1)

Challenge:	Experimental results show that crowdsourced annotations are highly effective under supervised conditions.
Approach:	They propose an annotator-aware representation learning model that is inspired by domain adaptation methods which attempt to capture effective domain-alike features.
Outcome:	The proposed model is highly effective on a benchmark dataset and achieves state-of-the-art performance with only a very small scale of expert annotations.

Copied to clipboard

José María Hoya Quecedo, Koppatz Maximilian, Roman Yangarber

Unsupervised Opinion Summarization as Copycat-Review Generation (2020.acl-main)

Challenge:	a method for disambiguating the lemma and part of speech of ambiguous words is proposed . a morphological analyser produces multiple analyses for ambiguously words .
Approach:	They propose a method for disambiguating the lemma and part of speech of ambiguous words in context . they use a large un-annotated corpus of text and a morphological analyser to train neural networks on the output of the analyser .
Outcome:	The proposed method outperforms the state-of-the-art on POS and lemma disambiguation in morphologically rich languages using no manual disambiguations or data annotations.

Copied to clipboard

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Towards Privacy-Aware Sign Language Translation at Scale (2024.acl-long)

Challenge:	Recent work on opinion summarization has focused on extracting fragments from reviews, but we use novel sentences to generate abstractive summaries.
Approach:	They propose an abstractive summarizer which does not use summaries in training and is trained end-to-end on a large collection of reviews.
Outcome:	The proposed model produces fluent and coherent summaries reflecting consensus opinions on Amazon and Yelp reviews.

Copied to clipboard

Phillip Rust, Bowen Shi, Skyler Wang, Necati Cihan Camgoz, Jean Maillard

Revisiting Modularized Multilingual NMT to Meet Industrial Demands (2020.emnlp-main)

Challenge:	Existing sign language training systems require detailed and time aligned annotations to be effective.
Approach:	They propose a two-stage framework for privacy-aware SLT at scale that leverages self-supervised video pretraining on anonymized and unannotated videos followed by supervised SLT finetuning on a curated parallel dataset.
Outcome:	The proposed framework outperforms baselines on the How2Sign dataset and achieves state-of-the-art finetuned and zero-shot gloss-free SLT performance.

Copied to clipboard

Sungwon Lyu, Bokyung Son, Kichang Yang, Jaekyoung Bae

ULTRA: Unleash LLMs’ Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement (2024.findings-acl)

Challenge:	Currently, the complete sharing of parameters for multilingual translation (1-1) is the most popular approach because of its compactness.
Approach:	They propose to use a multilingual neural machine translation model that only shares modules among the same languages as 1-1 to satisfy industrial requirements.
Outcome:	The proposed model can enjoy the benefits of multi-way training without the capacity bottleneck and low maintainability.

Copied to clipboard

Xinliang Frederick Zhang, Carter Blum, Temma Choji, Shalin Shah, Alakananda Vempala

WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020.acl-main)

Challenge:	Structural extraction of events within discourse is critical for event-centric understanding . document-level EAE focuses on arguments that are scattered across an entire document . ULTRA is a hierarchical framework that extracts event arguments more cost-effectively .
Approach:	They propose a hierarchical framework that extracts event arguments more cost-effectively . ULTRA sequentially reads text chunks of a document to generate a candidate argument set . they propose to use a supervised model to find the exact boundary of an argument .
Outcome:	The proposed framework outperforms strong models and ChatGPT by 9.8% when evaluated by Exact Match (EM).

Copied to clipboard

Hongming Zhang, Xinran Zhao, Yangqiu Song

Reasoning

Challenge:	a new task is developed to categorize essential commonsense knowledge for the Winograd Schema Challenge . a previous work focused on the classification of commonsensical knowledge by pre-trained models .
Approach:	They propose a task that categorizes essential commonsense knowledge for the Winograd Schema Challenge . they leverage the collected reasons to identify plausible reasons from wrong ones .
Outcome:	The proposed task aims to shed light on commonsense knowledge needed for better reasoning . it is based on the collected reasons and a new task called WinoWhy .

Do self-supervised speech models develop human-like perception biases? (2022.acl-long)

Copied to clipboard

Juliette Millet, Ewan Dunbar

Towards Distribution-shift Robust Text Classification of Emotional Content (2023.findings-acl)

Challenge:	Recent advances in speech recognition and representation learning show that self-supervised pretraining is an excellent way of improving performance while reducing the amount of labelled data needed for training.
Approach:	They compare the representational spaces of wav2vec, HuBERT and contrastive predictive coding (CPC) with the perceptual spaces of French-speaking and English-speaking human listeners.
Outcome:	The proposed models capture fine-grained perceptual phenomena while supervised models are better at capturing coarser, phone-level effects and effects of listeners’ native language on perception.

Copied to clipboard

Luana Bulla, Aldo Gangemi, Misael Mongiovi’

Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval (2022.emnlp-main)

Challenge:	Recent work has shown that supervised models are more robust to change in domain and distribution, but the decrease in performance due to the distribution shift is still a major issue for supervised systems.
Approach:	They propose to fine-tune supervised models on task-specific datasets to achieve out-of-distribution performance.
Outcome:	The proposed model outperforms all available models in distribution and out of distribution with only a few thousand training samples.

Copied to clipboard

Minjoon Jung, SeongHo Choi, JooChan Kim, Jin-Hwa Kim, Byoung-Tak Zhang

Multimodality

Challenge:	Existing studies have shown promising results in video corpus moment retrieval . however, they relied on the expensive query annotations for the VCMR .
Approach:	They propose a self-supervised learning framework to localize video corpus moment without annotations.
Outcome:	The proposed framework can localize the video corpus moment without any explicit annotation on TVR dataset.

Unsupervised Extractive Summarization of Emotion Triggers (2023.acl-long)

Copied to clipboard

Tiberiu Sosea, Hongli Zhan, Junyi Jessy Li, Cornelia Caragea

Efficient Zero-shot Event Extraction with Context-Definition Alignment (2022.findings-emnlp)

Challenge:	Recent approaches trained supervised models to detect emotions and explain emotion triggers via abstractive summarization, but this can block necessary responses.
Approach:	They propose to augment an abstractive dataset with extractive triggers and develop unsupervised models that can jointly detect emotions and summarize their triggers.
Outcome:	The proposed model outperforms existing models and is based on a COVID-19 crisis dataset.

Copied to clipboard

Hongming Zhang, Wenlin Yao, Dong Yu

Few-Shot Natural Language to First-Order Logic Translation via Code Generation (2025.naacl-long)

Challenge:	Conventional supervised methods cannot generalize to event types out of the pre-defined ontology.
Approach:	They propose to use two separate transformer models to model the definition semantics of an event type name into the same embedding space and then minimize their embeddable distance via contrastive learning.
Outcome:	The proposed model outperforms all previous zero-shot EE methods with fast inference speed due to the disjoint design.

Copied to clipboard

Junnan Liu

Modeling Graph Structure in Transformer for Better AMR-to-Text Generation (D19-1)

Challenge:	Recent studies have focused on translation of natural language to first-order logical formula (NL-FOL) but these methods face challenges such as inconsistency between training and inference phases and data-intensive finetuning process.
Approach:	They propose a method for translating natural language into first-order logical formulas using code snippets.
Outcome:	The proposed method surpasses training-free baselines and is comparable to supervised models trained on the full training data.

Copied to clipboard

Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, Guodong Zhou

Harnessing Toulmin’s theory for zero-shot argument explication (2024.acl-long)

Challenge:	Recent studies on AMR-to-text generation formalize the task as a sequence-tosequence learning problem . previous approaches only consider the relations between directly connected concepts while ignoring the rich structure in AMR graphs.
Approach:	They propose a structure-aware self-attention approach to model the relations between indirectly connected concepts in the seq2seq model.
Outcome:	The proposed approach outperforms the state-of-the-art on English AMR benchmarks . it significantly outperformed the state of the art on the benchmarks, with 29.66 and 31.82 BLEU scores .

Copied to clipboard

Ankita Gupta, Ethan Zuckerman, Brendan O’Connor

Unified Feature and Instance Based Domain Adaptation for Aspect-Based Sentiment Analysis (2020.emnlp-main)

Challenge:	To better analyze informal arguments on public forums, we propose the task of argument explication, which makes explicit a text’s argumentative structure and implicit reasoning by outputting triples of propositions claim, reason warrant.
Approach:	They propose to prompt generative large language models to output explicit argument components proposed by Toulmin by prompting with the theory name.
Outcome:	The proposed method evaluates the outputs’ coverage and validity through a human study and automatic evaluation based on prior argumentation datasets and performs robustness checks over alternative LMs, prompts, and argumentation theories.

Copied to clipboard

Chenggong Gong, Jianfei Yu, Rui Xia

Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining (2022.acl-long)

Challenge:	Existing approaches to aspect-based sentiment analysis rely on labeled data, but they lack the fine-grained labeles needed for the ABSA task.
Approach:	They propose a framework to perform feature adaptation and instance adaptation for the ABSA task . they learn domain-invariant feature representations by using part-of-speech features .
Outcome:	The proposed method improves on the state-of-the-art in two aspects of the ABSA task.

Copied to clipboard

Chih-chan Tien, Shane Steinert-Threlkeld

Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation (2020.acl-main)

Challenge:	a model trained to align only two languages can encode multilingually more aligned representations . a dual-pivot transfer theory is proposed for bilingual training .
Approach:	They propose methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts.
Outcome:	The proposed models reach the state of the art in unsupervised bitext mining and perform better than multilingually supervised models.

Copied to clipboard

Ning Ding, Dingkun Long, Guangwei Xu, Muhua Zhu, Pengjun Xie, Xiaobin Wang, Haitao Zheng

Text Classification via Large Language Models (2023.findings-emnlp)

Challenge:	Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS) however, they suffer from the cross-domain issue when they come to processing of out-of-domain data.
Approach:	They propose to use Chinese word as a target domain for distant annotation and adversarial training to reduce noise and maximize utilization of the source domain information.
Outcome:	The proposed method outperforms existing state-of-the-art methods on real-world datasets and significantly outperformed previous state- of-the art methods.

Copied to clipboard

Xiaofei Sun, Xiaoya Li, Jiwei Li, Fei Wu, Shangwei Guo, Tianwei Zhang, Guoyin Wang

Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories (2021.emnlp-main)

Challenge:	Large-scale Language Models (LLMs) have shown the ability for in-context learning.
Approach:	They propose a progressive reasoning strategy tailored to addressing complex linguistic phenomena such as intensification, contrast, irony and limited number of tokens allowed in in-context learning.
Outcome:	The proposed model performs better on 4 out of 5 widely-used text-classification benchmarks, while demonstrating comparable performance to SOTA on MR.

Copied to clipboard

Wenlin Yao, Xiaoman Pan, Lifeng Jin, Jianshu Chen, Dian Yu, Dong Yu

Major Entity Identification: A Generalizable Alternative to Coreference Resolution (2024.emnlp-main)

Challenge:	Existing supervised models struggle to make correct predictions on rare word senses due to limited training data.
Approach:	They propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge.
Outcome:	The proposed method outperforms previous methods on both frequent and rare word senses.

Copied to clipboard

Kawshik Sundar, Shubham Toshniwal, Makarand Tapaswi, Vineet Gandhi

Unknown Claims: Generation of Fact-Checking Training Examples from Unstructured and Structured Data (2024.emnlp-main)

Challenge:	Prior work identified annotation differences as one of the main reasons for the limited generalization gap in coreference resolution models.
Approach:	They propose an alternative referential task where the target entities are assumed to be specified in the input and the task is limited to the frequent entities.
Outcome:	The proposed model generalizes well across domains on multiple datasets with supervised models and LLM-based few-shot prompting.

Copied to clipboard

Jean-Flavien Bussotti, Luca Ragazzi, Giacomo Frisoni, Gianluca Moro, Paolo Papotti

Multimodality

Challenge:	Existing methods for fact-checking are labor-intensive and time-consuming.
Approach:	They propose a framework that generates training instances for FC systems automatically using textual and tabular content.
Outcome:	The proposed framework generates training instances for FC systems using textual and tabular content.

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model (2024.findings-emnlp)

Copied to clipboard

Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly, Debasis Samanta, Pabitra Mitra

Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization (2025.acl-long)

Challenge:	Existing studies show that training examples improve zero-shot performance of supervised ranking models.
Approach:	They propose to augment supervised ranking models with pairs of queries and documents to improve their performance.
Outcome:	The proposed model outperforms the unsupervised models on in-domain and out-domain retrieval benchmarks.

Copied to clipboard

Keane Ong, Rui Mao, Deeksha Varshney, Erik Cambria, Gianmarco Mengaldo

Robustness in NLP

Challenge:	Existing NLP methods lack robustness against greenwashed ESG content . existing methods often extract insights that reflect misleading or exaggerated sustainability claims rather than objective ESG performance.
Approach:	They propose to use a dataset to improve the robustness of ESG analysis amid the prevalence of greenwashing to analyze sustainability reports.
Outcome:	The proposed model improves robustness against greenwashed claims rather than objective ESG performance.

SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents (2024.emnlp-main)

Copied to clipboard

Qi Zhang, Zhijia Chen, Huitong Pan, Cornelia Caragea, Longin Latecki, Eduard Dragut

SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP (2025.emnlp-main)

Challenge:	Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data.
Approach:	They propose to use a scientific entity and relation extraction dataset to capture interactions between entities in full texts.
Outcome:	The proposed dataset captures the intricate use and interactions among entities in full texts and provides an out-of-distribution test set to offer a more realistic evaluation.

Copied to clipboard

Decheng Duan, Jitong Peng, Yingyi Zhang, Chengzhi Zhang

Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis (2023.findings-acl)

Challenge:	Existing datasets for structured information extraction focus on specific publication sections due to domain complexity and high cost of annotating scientific texts.
Approach:	They propose a specialized benchmark for full-text entity and relation extraction in the natural language processing domain.
Outcome:	The proposed dataset comprises 60 manually annotated full-text NLP publications covering 7,072 entities and 1,826 relations.

Copied to clipboard

Fan Qian, Jiqing Han, Yongjun He, Tieran Zheng, Guibin Zheng

Shoes-ACOSI: A Dataset for Aspect-Based Sentiment Analysis with Implicit Opinion Extraction (2024.findings-emnlp)

Challenge:	Existing studies have used general approaches to alleviate the overfitting of supervised models based on video data with sentiment annotations.
Approach:	They propose to capture common sentimental patterns in unlabeled videos using sentiment knowledge and non-verbal behavior to embed sentiment information into pre-trained multimodal representations.
Outcome:	The proposed model outperforms the baseline and achieves new State-Of-The-Art (SOTA) results.

Copied to clipboard

Joseph Peper, Wenzhao Qiu, Ryan Bruggeman, Yi Han, Estefania Chehade, Lu Wang

SCALE: Synergized Collaboration of Asymmetric Language Translation Engines (2024.findings-acl)

Challenge:	Prior work in ABSA has investigated opinion extraction as an important subtask, but these works only label concise, explicitly-stated opinion spans.
Approach:	They propose a new ABSA dataset with implicit opinion span annotations . they use paragraph-length inputs and prompted-LLM baselines to evaluate the dataset .
Outcome:	The proposed dataset presents significant challenges for fully-supervised models and LLMs.

Copied to clipboard

Xin Cheng, Xun Wang, Tao Ge, Si-Qing Chen, Furu Wei, Dongyan Zhao, Rui Yan

Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering (2024.findings-emnlp)

Challenge:	In this paper, we introduce SCALE, a collaborative framework that connects a compact Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine.
Approach:	They propose a collaborative framework that connects a Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine.
Outcome:	The proposed framework outperforms both LLMs and supervised models in high-resource or challenging low-resourced settings.

Copied to clipboard

Jiuheng Lin, Yuxuan Lai, Yansong Feng

MixRED: A Mix-lingual Relation Extraction Dataset (2024.lrec-main)

Challenge:	Existing methods for conditional question answering struggle with finding probable answers and identifying missing conditions.
Approach:	They propose a conditional question answering prompting approach that first identifies all conditions and constructs their logical relationships explicitly according to the document, then verifyes whether these conditions are satisfied and finally solves the logical expression to indicate any missing conditions.
Outcome:	The proposed method outperforms existing prompting baselines on two CQA benchmark datasets and can facilitate GPT-3.5-Turbo or GPT-4 to outperFORM all existing supervised models.

Copied to clipboard

Lingxing Kong, Yougang Chu, Zheng Ma, Jianbing Zhang, Liang He, Jiajun Chen

MKeCL: Medical Knowledge-Enhanced Contrastive Learning for Few-shot Disease Diagnosis (2024.lrec-main)

Challenge:	Existing research focuses on monolingual relation extraction, but there is a significant gap in understanding relation extraction in the mix-lingual scenario.
Approach:	They propose a task of considering relation extraction in the mix-lingual scenario . they construct a human-annotated dataset to support the task .
Outcome:	The proposed task evaluates state-of-the-art supervised models and large language models on the human-annotated dataset MixRED.

Copied to clipboard

Yutian Zhao, Huimin Wang, Xian Wu, Yefeng Zheng

Aligning Predictive Uncertainty with Clarification Questions in Grounded Dialog (2023.findings-emnlp)

Challenge:	Existing approaches to disease classification are limited in real-world clinics due to insufficient data and inflexibility.
Approach:	They propose a medical knowledge-Enhanced Contrastive Learning approach to disease diagnosis . they incorporate medical knowledge graphs and medical licensing exams in modeling .
Outcome:	The proposed model outperforms existing models on real clinical EMRs on a single patient.

Copied to clipboard

Kata Naszadi, Putra Manggala, Christof Monz

Natural Language Interfaces

Challenge:	Previous work bases the timing of questions on supervised models learned from interactions between humans.
Approach:	They propose to ground the need for questions in the acting agent's predictive uncertainty by using the T5 encoder-decoder architecture to solve a Minecraft Collaborative Building task.
Outcome:	The proposed model can detect ambiguous instructions and predict responses better than previous models.

Easy as PIE? Identifying Multi-Word Expressions with LLMs (2025.emnlp-main)

Copied to clipboard

Kai Golan Hashiloni, Ofri Hefetz, Kfir Bar

TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation (2025.findings-emnlp)

Challenge:	Multiword expressions (MWEs) are a semantically non-compositional subclass of multiword expression . authors show that prompt-based LLMs can perform competitively with supervised models .
Approach:	They propose a prompt-based approach to identify idiomatic expressions in running text . they find prompt-driven LLMs can perform competitively with supervised models .
Outcome:	The proposed approach can perform well with supervised models on annotated data.

Copied to clipboard

Armel Randy Zebaze, Benoît Sagot, Rachel Bawden

Sequence-to-Sequence Language Models for Character and Emotion Detection in Dream Narratives (2024.lrec-main)

Challenge:	In-context learning and similarity search have been shown to improve LLMs' performance in machine translation, but they lag behind when dealing with low-resource languages.
Approach:	They propose a method that uses an LLM to generate topic-specific target-side data in the LRL.
Outcome:	The proposed approach boosts LLM translation performance during in-context learning and fine-tuning.

Copied to clipboard

Gustave Cortal

LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World (2025.findings-acl)

Challenge:	Sigmund Freud's interpretation of dreams has been central to understanding human consciousness for centuries.
Approach:	They propose to automate the annotation process by using a natural language framework . they evaluate the impact of model size, prediction order of characters, and consideration of proper names and character traits .
Outcome:	The proposed model performs better with a large language model while having 28 times fewer parameters.

Copied to clipboard

Sina Semnani, Pingyue Zhang, Wanyue Zhai, Haozhuo Li, Ryan Beauchamp, Trey Billing, Katayoun Kishi, Manling Li, Monica Lam

Leveraging What’s Overfixed: Post-Correction via LLM Grammatical Error Overcorrection (2025.emnlp-main)

Challenge:	Using a partially reannotated subset of the Armed Conflict Location & Event Data, we analyze 39,786 conflict events across 20 languages and 171 countries.
Approach:	They propose a large-scale conflict event dataset with extensive coverage of region-specific entities.
Outcome:	The proposed method detects event arguments and entities through holistic document understanding and normalizes them across the multilingual dataset.

Copied to clipboard

Taehee Park, Heejin Do, Gary Lee

The Noisy Path from Source to Citation: Measuring How Scholars Engage with Past Research (2025.acl-long)

Challenge:	Existing methods to reduce overcorrection often result in significantly decreased recall, limiting the usability of correction systems.
Approach:	They propose a novel approach that leverages the strengths of large language models to balance recall and precision by triggering overcorrection via LLMs and fine-tuning smaller models to identify and refine erroneous outputs.
Outcome:	The proposed approach maximizes recall and precision by leveraging the generative power of LLMs while preserving the reliability of smaller supervised models.

Copied to clipboard

Hong Chen, Misha Teplitskiy, David Jurgens

Challenge:	Academic citations are widely used for evaluating research and tracing knowledge flows.
Approach:	They propose a computational pipeline to quantify citation fidelity at the sentence level by identifying citations in citing papers and corresponding claims in cited papers.
Outcome:	The proposed pipeline identifies citations in citing papers and the corresponding claims in cited papers and applies supervised models to measure fidelity at the sentence level.

WojoodRelations: Arabic Relation Extraction Corpus and Modeling (2025.emnlp-main)

Copied to clipboard

Alaa Aljabari, Mohammed Khalilia, Mustafa Jarrar