DEEP LEARNING METHODS

Graph-based Deep Learning in Natural Language Processing (D19-2)

Challenge:	Efficient access to mentions of clinical entities is very important for using clinical text.
Approach:	They developed a pipeline system based on deep learning methods for this shared task . it achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average LSTM score of 0.8391 on track 2 .
Outcome:	The proposed system achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average score of 0.8391 on track 2.

Copied to clipboard

Shikhar Vashishth, Naganand Yadati, Partha Talukdar

Multimodality

Challenge:	This tutorial aims to introduce graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for Natural Language Processing (NLP)
Approach:	It provides a brief introduction to graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for Natural Language Processing (NLP).
Outcome:	This tutorial provides a brief introduction to graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for natural language processing (NLP).

Deep neural model with enhanced embeddings for pharmaceutical and chemical entities recognition in Spanish clinical text (D19-57)

Copied to clipboard

Renzo Rivera, Paloma Martínez

Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text (D19-62)

Challenge:	Currently, the number of biomedical literature is growing at an exponential rate.
Approach:	They propose a Deep Learning architecture for pharmaceutical and chemical Named Entity Recognition in Spanish clinical cases texts.
Outcome:	The proposed model outperforms the state-of-the-art methods on the PharmaCoNER corpus . the proposed model is based on two bidirectional long-term memory and conditional random field networks .

Copied to clipboard

Prasadith Kirinde Gamaarachchige, Diana Inkpen

Low-Resource NLP

Challenge:	Existing methods for mental illness detection have limited data available for training . lack of sufficient annotated data and inability to extract explanations on the derived outcome have restricted researchers to use traditional methods.
Approach:	They propose to use emotional patterns identified by clinical practitioners to enhance the prediction capabilities of a mental illness detection model built using a deep neural network architecture.
Outcome:	The proposed method achieves a task-specific AUC higher than 0.90 . it compares multi-task learning with multi-channel convolutional neural network and multiple inputs to methods such as multi-class classification .

Training a Ranking Function for Open-Domain Question Answering (N18-4)

Copied to clipboard

Phu Mon Htut, Samuel Bowman, Kyunghyun Cho

Question Answering

Challenge:	Recent advances in machine reading have inspired researchers to combine Information Retrieval with machine reading to tackle open-domain QA.
Approach:	They propose two neural network rankers that assign scores to different passages based on their likelihood of containing the answer to a given question.
Outcome:	The proposed models achieve human level performance in open-domain QA compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question.

Automated Screening of Antibacterial Nanoparticle Literature: Dataset Curation and Model Evaluation (2026.eacl-long)

Copied to clipboard

Alperen Ozturk, Şaziye Betül Özateş, Sophia Bahar Root, Angela Violi, Nicholas Kotov, J. Scott VanEpps, Emine Sumeyra Turali Emre

Challenge:	Antimicrobial resistance is a growing global health threat, driving interest in nanoparticle-based alternatives to conventional antibiotics.
Approach:	They propose to use machine learning to classify scientific abstracts using inorganic nanoparticles with intrinsic antibacterial properties.
Outcome:	The proposed method distinguishes intrinsic antibacterial NPs from studies focusing on drug carriers or surface-bound applications.

Regularized Graph Convolutional Networks for Short Text Classification (2020.coling-industry)

Copied to clipboard

Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian, Vipin Kumar

ArMATH: a Dataset for Solving Arabic Math Word Problems (2022.lrec-1)

Challenge:	Short text classification is a problem in natural language processing, social network analysis, and e-commerce.
Approach:	They propose a short text classification technique that incorporates label dependencies into the output space to overcome the limitations of short text.
Outcome:	The proposed model outperforms baseline methods on proprietary and external datasets and is more robust to noise in textual features.

Copied to clipboard

Reem Alghamdi, Zhenwen Liang, Xiangliang Zhang

Numerical Reasoning

Challenge:	This paper is the first to use deep learning methods to solve Arabic MWPs . it is also the first study to use transfer learning to solve MWp across different languages .
Approach:	They contribute to the first large-scale dataset for Arabic Math Word Problems . they use deep learning methods to solve Arabic MWPs and a transfer learning model to promote performance .
Outcome:	The proposed model improves Arabic MWP solvers by 3% over the existing model.

Sentiment Analysis of Yelp Review Dataset: A Comparative Study of Machine Learning Methods (2026.acl-srw)

Copied to clipboard

Krishna Thakar, Mohamed Abu Sheha, Emmanuel Thompson

Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (D19-1)

Challenge:	Existing methods for sentiment analysis are inconsistent and require manual processing.
Approach:	They use natural language processing and machine learning to classify Yelp reviews' sentiments.
Outcome:	The proposed model outperforms other models on Yelp reviews.

Copied to clipboard

Thiago Castro Ferreira, Chris van der Lee, Emiel van Miltenburg, Emiel Krahmer

Text Generation

Challenge:	Traditionally, data-to-text applications have been designed using a modular pipeline architecture, in which the non-linguistic input data is converted into natural language through several intermediate transformations.
Approach:	They propose to use Gated-Recurrent Units and Transformer to implement neural pipelines for data-to-text generation.
Outcome:	The proposed models generalize better to unseen inputs and have better performance than the existing pipeline architectures.

A Stacking-based Efficient Method for Toxic Language Detection on Live Streaming Chat (2022.emnlp-industry)

Copied to clipboard

Yuto Oikawa, Yuki Nakayama, Koji Murakami

Green & Sustainable NLP

Challenge:	Existing methods for toxic language detection are based on deep learning, but they are not scalable considering inference speed and computational resources.
Approach:	They propose a method for toxic language detection that is aware of real-world scenarios by partial stacking partial stacks that feeds initial results with low confidence to meta-classifier.
Outcome:	The proposed method achieves faster inference speed than BERT-based models with comparable performance.

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction (2025.naacl-long)

Copied to clipboard

Jie Feng, Yuwei Du, Jie Zhao, Yong Li

Language Models

Challenge:	Existing methods to apply large language models to zero-shot next location prediction tasks are limited due to their limited computational power.
Approach:	They propose a systematic agentic prediction framework to achieve generalized next location prediction.
Outcome:	The proposed framework surpasses the leading baseline by 3.33% to 8.57% across 8 out of 12 metrics.

Subword-augmented Embedding for Cloze Reading Comprehension (C18-1)

Copied to clipboard

Zhuosheng Zhang, Yafang Huang, Hai Zhao

Representation Learning

Challenge:	Existing models for machine reading comprehension use word and character representations, but character is not the minimal unit.
Approach:	They propose to use subword rather than character for word embedding enhancement . they also empirically explore different augmentation strategies on subword-augmented embedded embedders .
Outcome:	The proposed model outperforms state-of-the-art models on public datasets.

Genre Identification and the Compositional Effect of Genre in Literature (C18-1)

Copied to clipboard

Joseph Worsham, Jugal Kalita

Multilingual and cross-lingual document classification: A meta-learning approach (2021.eacl-main)

Challenge:	Literature is artistic and conveys complex themes over the course of very long narratives.
Approach:	They propose a method which can work with large literary corpus of texts . they propose 'gutenberg' dataset to perform Genre Identification .
Outcome:	The proposed methods improve results in a literature-based task with 200,000 words of literature . the Gutenberg dataset is used to model literary classifications with a high level of fidelity .

Copied to clipboard

Niels van der Heijden, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova

Multilingual Stance Detection in Tweets: The Catalonia Independence Corpus (2020.lrec-1)

Challenge:	Existing methods to document classification in low-resource languages are under-resourced . 6% of the world's languages are spoken, and many have inadequate resources .
Approach:	They propose a meta-learning approach to document classification in low-resource languages . they propose 'nuclear-shot' cross-lingual adaptation to previously unseen languages based on limited data .
Outcome:	The proposed method performs on-par on some languages while under-resourced in others.

Copied to clipboard

Elena Zotova, Rodrigo Agerri, Manuel Nuñez, German Rigau

Word Emotion Induction for Multiple Languages as a Deep Multi-Task Learning Problem (N18-1)

Challenge:	stance detection is a method to determine the attitude of a text with respect to a specific topic or claim.
Approach:	They propose a multilingual dataset for stance detection in Twitter for the Catalan and Spanish languages.
Outcome:	The proposed dataset shows that it is well balanced for multilingual and cross-lingual research.

Copied to clipboard

Sven Buechel, Udo Hahn

Language Models

Challenge:	a recent shift towards expressive emotion representation models has hampered deep learning in sentiment analysis.
Approach:	They propose a multi-task learning problem to solve a language data bottleneck . they propose to use word emotion induction as an individual task to predict emotion .
Outcome:	The proposed model outperforms a wide range of other methods on 9 languages and 15 conditions.

A Review on Deep Learning Techniques Applied to Answer Selection (C18-1)

Copied to clipboard

Tuan Manh Lai, Trung Bui, Sheng Li

Question Answering

Challenge:	Existing deep learning methods for answer selection are not feature engineering or expensive external resources.
Approach:	They propose to use deep learning methods to analyze and predict answer quality . they use a set of candidate answers to identify which of the candidates answers the question correctly.
Outcome:	The proposed methods produce impressive performance without feature engineering or expensive external resources.

Hybrid Attention based Multimodal Network for Spoken Language Classification (C18-1)

Copied to clipboard

Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic

Learning Word Ratings for Empathy and Distress from Document-Level User Responses (2020.lrec-1)

Challenge:	Using linguistic content and vocal characteristics for multimodal deep learning is difficult for computers to interpret human meaning .
Approach:	They propose a deep multimodal network with feature attention and modality attention to classify utterance-level speech data.
Outcome:	The proposed system achieves state-of-the-art or competitive results on three published multimodal datasets.

Copied to clipboard

João Sedoc, Sven Buechel, Yehonathan Nachmany, Anneke Buffone, Lyle Ungar

Chat-Ghosting: Methods for Auto-Completion in Dialog Systems (2026.eacl-long)

Challenge:	Emotion analysis of text is increasing in popularity in NLP, however, manually creating lexica for psychological constructs such as empathy has proven difficult.
Approach:	They compare different approaches to learning word ratings from higher-level supervision and use a Mixed-Level Feed Forward Network to create the first-ever empathy lexicon.
Outcome:	The proposed model automatically creates empathy word ratings from document-level ratings.

Copied to clipboard

Anubhab Mandal, Sandeep Mishra, Bishal Santra, Tushar Abhishek, Pawan Goyal, Manish Gupta

Dialogue Systems & Conversational Agents

Challenge:	Ghosting is a type-ahead completion task that predicts a user's intended input for inline query auto-completion (QAC).
Approach:	They propose to use ghosting to predict a user's intended input for inline query auto-completion by suggesting completions to incomplete queries.
Outcome:	The proposed method outperforms deep learning and deep learning methods with and without dialog context for ghosting.

Weak Supervision for Learning Discourse Structure (D19-1)

Copied to clipboard

Sonia Badene, Kate Thompson, Jean-Pierre Lorré, Nicholas Asher

Multimodality

Challenge:	a weak supervision approach is a promising tool for learning discourse structure for multi-party dialogue.
Approach:	They propose a data programming paradigm that allows a user to label training data using expert-composed heuristics and transform them into probability distributions of the class labels.
Outcome:	The proposed approach outperforms both deep learning and traditional ML approaches on the task of learning discourse structure for multi-party dialogue.

Learning Numeral Embedding (2020.findings-emnlp)

Copied to clipboard

Chengyue Jiang, Zhonglin Nian, Kaihao Guo, Shanbo Chu, Yinggong Zhao, Libin Shen, Kewei Tu

Representation Learning

Challenge:	Existing word embedding methods do not learn numeral embedds well because numerals are limited in number and their appearances in training corpora are highly scarce.
Approach:	They propose two numeral embedding methods that can handle the out-of-vocabulary problem for numerals.
Outcome:	The proposed methods can handle the out-of-vocabulary problem for numerals.

WIKIR: A Python Toolkit for Building a Large-scale Wikipedia-based English Information Retrieval Dataset (2020.lrec-1)

Copied to clipboard

Jibril Frej, Didier Schwab, Jean-Pierre Chevallet

Automated Discovery of Mathematical Definitions in Text (2020.lrec-1)

Challenge:	ad-hoc information retrieval methods usually require large amounts of annotated data to be effective.
Approach:	They propose an open-source toolkit to automatically build large-scale English information retrieval datasets based on Wikipedia.
Outcome:	The proposed toolkit builds large-scale English information retrieval datasets based on Wikipedia with 59,252 queries and 2,617,003 pairs.

Copied to clipboard

Natalia Vanetik, Marina Litvak, Sergey Shevchuk, Lior Reznik

Numerical Reasoning

Challenge:	a recent study shows that definition extraction is inefficient for one-sentence definitions . definitions are used in many automatic text analysis tasks, including ontology matching and construction .
Approach:	They propose to use convolutional neural network and recurrent neural network to identify mathematical definitions from one sentence.
Outcome:	The proposed dataset shows that deep learning methods can identify definitions from mathematical texts.

A Low-Cost Motion Capture Corpus in French Sign Language for Interpreting Iconicity and Spatial Referencing Mechanisms (2022.lrec-1)

Copied to clipboard

Clémence Mertz, Vincent Barreaud, Thibaut Le Naour, Damien Lolive, Sylvie Gibet

Explainability & Interpretability in NLP

Challenge:	Existing tools for automatic translation of sign language videos into transcribed texts are limited.
Approach:	They propose to use deep learning methods to circumvent the use of models in spatial referencing recognition by a 3D skeleton and a software program to capture and post-process the LSF-SHELVES corpus.
Outcome:	The proposed system targets iconicity and spatial referencing in french sign language . it is light-weight and low-cost to collect data from a large panel of signers .

ISO-based Annotated Multilingual Parallel Corpus for Discourse Markers (2022.lrec-1)

Copied to clipboard

Purificação Silvano, Mariana Damova, Giedrė Valūnaitė Oleškevičienė, Chaya Liebeskind, Christian Chiarcos, Dimitar Trajanov, Ciprian-Octavian Truică, Elena-Simona Apostol, Anna Baczkowska

Multilinguality

Challenge:	Discourse markers carry information about the discourse structure and organization, and also signal local dependencies or epistemic stance of speaker.
Approach:	They propose an ISO-based annotated multilingual parallel corpus for discourse markers . they propose an annotation scheme for discourse relations with a plug-in to ISO 24617-2 .
Outcome:	The proposed language resource is based on an ISO-based annotated multilingual parallel corpus of discourse markers.

Complex Word Identification: A Comparative Study between ChatGPT and a Dedicated Model for This Task (2024.lrec-main)

Copied to clipboard

Abdelhak Kelious, Mathieu Constant, Christophe Coeur

Language Models

Challenge:	Existing methods to assess lexical complexity are used to evaluate the difficulty of vocabulary for language learners.
Approach:	They propose to use pre-trained language models to assess the complexity of a word based on its context.
Outcome:	The proposed method outperforms the best systems in SemEval-2021.

CxGBERT: BERT meets Construction Grammar (2020.coling-main)

Copied to clipboard

Harish Tayyar Madabushi, Laurence Romain, Dagmar Divjak, Petar Milin

Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations (2022.coling-1)

Challenge:	lexico-semantic elements capture a large amount of linguistic information, but they do not capture all information contained in text.
Approach:	They propose to use BERT to train a model that uses a deep bidirectional transformer to capture a significant amount of lexico-semantic information.
Outcome:	The proposed model captures lexico-semantic information, but it is redundantly encoded in lexical information.

Copied to clipboard

Wessel Poelman, Rik van Noord, Johan Bos

Improving Hate Speech Detection with Deep Learning Ensembles (L18-1)

Challenge:	Existing semantic parsers are based on deep learning, but rule-based approaches offer advantages . a drawback of neural semantic parses is that their output lacks explainability .
Approach:	They propose a method that maps a syntactic dependency tree to a formal meaning representation using a series of graph transformations.
Outcome:	The proposed method outperforms neural parsers in English, German, Italian and Dutch.

Copied to clipboard

Steven Zimmerman, Udo Kruschwitz, Chris Fox

Responsible & Trustworthy NLP

Challenge:	censorship is a potential risk when addressing these issues with automated text classification methods.
Approach:	They propose to use a neural network-based ensemble method to better classify hate speech using a publicly available embedding model and a popular sentiment dataset.
Outcome:	The proposed method improves by 5 points on a hate speech corpus from Twitter and a popular sentiment dataset.

Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation (2020.findings-emnlp)

Copied to clipboard

Nithin Holla, Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova

Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages (2020.coling-main)

Challenge:	Existing methods for word sense disambiguation (WSD) are limited and require large datasets annotated with word senses.
Approach:	They propose a meta-learning framework for few-shot word sense disambiguation where the goal is to learn to disambiguate unseen words from only a few labeled instances.
Outcome:	The proposed framework is based on a large training dataset and a small number of examples.

Copied to clipboard

Efsun Sarioglu Kayi, Linyong Nan, Bohan Qu, Mona Diab, Kathleen McKeown

Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts (2024.lrec-main)

Challenge:	We train monolingual and cross-lingual classifiers on the extracted features of tweets . we use a few state-of-the-art contextual embeddings to extract features of the tweets.
Approach:	They propose to use tweets to train a dataset of English and two low-resource languages to train zero-shot transfer models.
Outcome:	The proposed model performs well in English and in low-resource languages . the proposed model is based on state-of-the-art embeddings and semi-supervised methods .

Copied to clipboard

Thibault Clerice

CLFD: A Novel Vectorization Technique and Its Application in Fake News Detection (2020.lrec-1)

Challenge:	a traditional approach to corpus building involves constructing a corpus centered around specific themes, such as colors.
Approach:	They propose to use deep learning methods to accelerate corpus building in humanities . they propose to integrate metadata embeddings into the model to improve accuracy .
Outcome:	The proposed method outperforms token-based searches in the humanities and linguistics field.

Copied to clipboard

Michail Mersinias, Stergos Afantenos, Georgios Chalkiadakis

Responsible & Trustworthy NLP

Challenge:	Existing work on fake news detection is limited due to the complex nature of the news .
Approach:	They propose a statistical approach for the generation of feature vectors to describe a document . they use class label frequency distance to boost machine learning methods .
Outcome:	The proposed method outperforms deep learning methods in large datasets while outperforming traditional methods.

Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues (2026.findings-acl)

Copied to clipboard

Zory Zhang, Pinyuan Feng, Bingyang Wang, Tianwei Zhao, Suyang Yu, Qingying Gao, Hokin Deng, Ziqiao Ma, Yijiang Li, Dezhi Luo

Natural Language Interfaces

Challenge:	Where someone looks is a nonverbal communication cue that children and adults readily use.
Approach:	They used 1,360 real-world photos to construct evaluation stimuli for Vision-Language Models (VLMs) they found a substantial performance gap between VLMs and humans .
Outcome:	The proposed model outperforms existing models in predicting gaze direction using head orientation rather than eye appearance.

Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Copied to clipboard

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu

Machine Translation

Challenge:	Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach:	They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome:	The proposed method outperforms baseline methods on small and large scale machine translation datasets.

Reconstructing NER Corpora: a Case Study on Bulgarian (2020.lrec-1)

Copied to clipboard

Iva Marinova, Laska Laskova, Petya Osenova, Kiril Simov, Alexander Popov

CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction (2024.emnlp-main)

Challenge:	Named Entity Recognition (NER) and Named Enel Linking (NEL) are two related tasks that are under-resourced for the Slavic languages.
Approach:	They propose to use deep learning methods to improve a Named Entity Recognition corpus and to predict and annotate new types in a test corpus.
Outcome:	The proposed model improves a type-based Named Entity Recognition (NER) training corpus and predicts and annotates new types in a test corpus.

Copied to clipboard

Tuan Nguyen, Thanh Huynh, Minh Hieu Phan, Quoc Viet Hung Nguyen, Phi Le Nguyen

Representation Learning

Challenge:	Existing deep learning methods require large datasets to achieve high generalizability.
Approach:	They propose a framework that enhances deep learning models with clinical rationales derived from medically proficient Large Language Models.
Outcome:	The proposed framework outperforms state-of-the-art models on two tasks using two popular EHR datasets by up to 11.2%.

An Empirical Examination of Online Restaurant Reviews (2020.lrec-1)

Copied to clipboard

Hyun Jung Kang, Iris Eshkol-Taravella

Dataset Creation and Evaluation of Aspect Based Sentiment Analysis in Telugu, a Low Resource Language (2020.lrec-1)

Challenge:	Existing methods for opinion mining and sentiment analysis focus on extracting either positive or negative opinions from texts and determining the targets of these opinions.
Approach:	They propose a corpus-based scheme that detects evaluative language at a finer-grained level.
Outcome:	The proposed scheme classifies each sentence into one of four evaluation types based on the proposed scheme.

Copied to clipboard

Yashwanth Reddy Regatte, Rama Rohit Reddy Gangula, Radhika Mamidi

Multi-Task Stance Detection with Sentiment and Stance Lexicons (D19-1)

Challenge:	Aspect Based Sentiment Analysis (ABSA) is a finer level sentiment analysis that assigns polarity to each targeted aspect instead of the entire review.
Approach:	They propose to use Telugu as a language for aspect based sentiment analysis . they use a resource that can be used to classify and categorise aspects of a review .
Outcome:	The proposed resource is based on a set of tasks in Telugu which demonstrate its reliability and usefulness.

Copied to clipboard

Yingjie Li, Cornelia Caragea