AUXILIARY TASK

Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identification (2022.acl-long)

Challenge:	Existing approaches to Chinese Named Entity Recognition (NER) lack explicit word boundary and tenses information.
Approach:	They propose a boundary enhanced approach for Chinese Named Entity Recognition . they add an additional Graph Attention Network(GAT) layer to capture internal dependency of phrases .
Outcome:	The proposed approach improves Chinese Named Entity Recognition (NER) on OntoNotes and Weibo corpora.

Copied to clipboard

George-Eduard Zaharia, Răzvan-Alexandru Smădu, Dumitru Cercel, Mihai Dascalu

An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity Recognition (2022.acl-long)

Challenge:	Existing datasets for complex word identification (CWI) are limited and the difficulty of the task is augmented by the scarcity of input examples.
Approach:	They propose a novel training technique for the complex word identification task based on domain adaptation to improve character and context representations.
Outcome:	The proposed training technique improves the target character and context representations and also smooths differences between datasets.

Copied to clipboard

Zhuoran Li, Chunming Hu, Xiaohui Guo, Junfan Chen, Wenyi Qin, Richong Zhang

Named Entity Recognition in Multi-level Contexts (2020.aacl-main)

Challenge:	Existing models for named entity recognition only consider the potential transferability between two identical tasks across both domains.
Approach:	They propose to use a similarity metric model to improve cross-lingual named entity recognition task on target domain.
Outcome:	Empirical studies on 7 different languages confirm the effectiveness of the proposed model.

Copied to clipboard

Yubo Chen, Chuhan Wu, Tao Qi, Zhigang Yuan, Yongfeng Huang

An Improved Model for Voicing Silent Speech (2021.acl-short)

Challenge:	Existing methods for named entity recognition are unsatisfactory for recognizing entities in limited or ambiguous sentence-level contexts.
Approach:	They propose a framework to incorporate multi-level contexts for named entity recognition using TagLM as a baseline model and an auxiliary task to mine word-level contextual information.
Outcome:	The proposed framework is based on a set of sentence-level contexts and a document-level task to mine word-level contextual information.

Copied to clipboard

David Gaddy, Dan Klein

A Span-based Dynamic Local Attention Model for Sequential Sentence Classification (2021.acl-short)

Challenge:	Existing models for voicing silent speech use hand-designed features instead of EMG signals.
Approach:	They propose to use facial electromyography signals as input instead of hand-designed features to give the model greater flexibility to learn its own features.
Outcome:	The proposed model improves state-of-the-art on an open vocabulary intelligibility evaluation by 25.8%.

Copied to clipboard

Xichen Shang, Qianli Ma, Zhenxi Lin, Jiangyue Yan, Zipeng Chen

Transductive Auxiliary Task Self-Training for Neural Multi-Task Models (D19-61)

Challenge:	Existing methods for sentence classification ignore latent segment structure of document, in which contiguous sentences have coherent semantics.
Approach:	They propose a span-based dynamic local attention model that captures structural information by supervised dynamic local focus.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets.

Copied to clipboard

Johannes Bjerva, Katharina Kann, Isabelle Augenstein

Paper Bullets: Modeling Propaganda with the Help of Metaphor (2023.findings-eacl)

Challenge:	Multi-task learning and self-training are two common ways to improve a machine learning model’s performance in settings with limited training data.
Approach:	They propose a transductive auxiliary task self-training procedure that trains a model on auxiliary tasks and test instances with auxiliary labels generated by a single-task version of the model.
Outcome:	The proposed method improves accuracy by 9.56% over the pure multi-task model for dependency relation tagging and 13.03% for semantic taging.

Copied to clipboard

Daniel Baleato Rodríguez, Verna Dankers, Preslav Nakov, Ekaterina Shutova

Challenge:	We hypothesize that it can be beneficial to model propaganda and metaphor together . we identify propaganda using loaded language and name-calling .
Approach:	They hypothesize that it can be beneficial to model propaganda and metaphor together . they use two datasets to identify propaganda techniques in news articles and memes .
Outcome:	The proposed model improves performance for the two most common propaganda techniques, especially loaded language and name-calling.

Dynamic Multi-Level Multi-Task Learning for Sentence Simplification (C18-1)

Copied to clipboard

Han Guo, Ramakanth Pasunuru, Mohit Bansal

Paraphrasing

Challenge:	Sentence simplification is the task of improving readability and understandability of an input text.
Approach:	They propose a strong pointer-copy mechanism based sequence-to-sequence sentence simplification model and a novel ‘multi-level’ soft sharing approach where each auxiliary task shares different (higher versus lower) level layers of the model.
Outcome:	The proposed model outperforms competing simplification systems in SARI and FKGL automatic metrics, and human evaluation.

Predicting and Using Target Length in Neural Machine Translation (2020.aacl-main)

Copied to clipboard

Zijian Yang, Yingbo Gao, Weiyue Wang, Hermann Ney

Machine Translation

Challenge:	Current NMT systems do not model the length of the output explicitly . length normalization is a common technique used in the beam search of NMT to enable a fair comparison of partial hypotheses with different lengths.
Approach:	They propose to use length prediction as an auxiliary task to obtain length information from the encoder.
Outcome:	The proposed sub-network improves over the baseline system and the predicted length can be used as an alternative to length normalization during decoding.

LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization (2020.coling-main)

Copied to clipboard

Nurul Lubis, Christian Geishauser, Michael Heck, Hsien-chin Lin, Marco Moresi, Carel van Niekerk, Milica Gasic

Perturbation-driven Dual Auxiliary Contrastive Learning for Collaborative Filtering Recommendation (2025.coling-main)

Challenge:	Reinforcement learning (RL) can be used to steer a conversation towards successful task completion.
Approach:	They propose to use latent latent variables to shape latent variable distributions . they use response auto-encoding as auxiliary task to capture generative factors .
Outcome:	The proposed approach yields a more action-characterized latent representations . the proposed approach achieves state-of-the-art success rates .

Copied to clipboard

Caihong Mu, Keyang Zhang, Jialiang Zhou, Yi Liu

KESA: A Knowledge Enhanced Approach To Sentiment Analysis (2022.aacl-main)

Challenge:	Existing contrastive learning-based methods struggle with data sparsity in real-world recommendations . Graph collaborative filtering incorporates contrastive training as an auxiliary task to improve performance .
Approach:	They propose a perturbation-driven dual auxiliary contrastive learning task for collaborative filtering . structure perturbation and weight perturbation are used to construct two graphs .
Outcome:	The proposed model outperforms benchmark models on multiple public datasets.

Copied to clipboard

Qinghua Zhao, Shuai Ma, Shuo Ren

Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework (2020.coling-main)

Challenge:	Recent work on injecting sentiment knowledge into pre-trained language models, but it is difficult to integrate external knowledge into PLMs.
Approach:	They propose two sentiment-aware auxiliary tasks to integrate sentiment knowledge into the objective of the downstream task.
Outcome:	The proposed tasks outperform baselines and complement existing sentiment-enhanced models.

Copied to clipboard

Shweta Yadav, Jainish Chauhan, Joy Prakash Sain, Krishnaprasad Thirunarayan, Amit Sheth, Jeremiah Schumm

Improving Context Modeling in Neural Topic Segmentation (2020.aacl-main)

Challenge:	Existing studies on social media for deriving mental health status of users focus on the depression detection task.
Approach:	They propose to use a BERT based robust multi-task learning framework to accurately identify the depressive symptoms using the auxiliary task of figurative usage detection.
Outcome:	The proposed model improves its robustness and reliability for distinguishing the depression symptoms.

Copied to clipboard

Linzi Xing, Brad Hackinen, Giuseppe Carenini, Francesco Trebbi

Challenge:	Recent work favors highly effective neural supervised approaches for topic segmentation but current neural solutions are limited in how they model context.
Approach:	They propose to enhance a hierarchical attention biLSTM network-based topic segmenter to better model context by adding a coherence-related auxiliary task and restricted self-attention.
Outcome:	The proposed model outperforms SOTA approaches on three datasets and on four real-world benchmarks.

From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction (2022.findings-emnlp)

Copied to clipboard

Xiuyu Wu, Yunfang Wu

Learning High-Quality and General-Purpose Phrase Representations (2024.findings-eacl)

Challenge:	Chinese Grammatical Error Correction (CGEC) aims to generate correct sentences from erroneous sequences.
Approach:	They propose a zero-shot approach for spelling error correction that is simple but effective . they propose auxiliary task to predict POS sequence of target sentence .
Outcome:	The proposed framework achieves 42.11 F-0.5 on the English GEC dataset outperforms the previous state-of-the-art by a wide margin of 1.30 points.

Copied to clipboard

Lihu Chen, Gael Varoquaux, Fabian Suchanek

Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks (2024.findings-eacl)

Challenge:	Pre-trained language models for phrasal embeddings are unnecessarily complex and require to be pre-tuned on a corpus with context sentences.
Approach:	They propose a framework to learn phrase representations in a context-free fashion.
Outcome:	The proposed framework generates superior phrase embeddings while requiring a smaller model size.

Copied to clipboard

Danae Sanchez Villegas, Daniel Preotiuc-Pietro, Nikolaos Aletras

Text Classification

Challenge:	Prior work on multimodal content classification has not addressed these challenges.
Approach:	They propose to use two auxiliary tasks to fine-tune multimodal models to address hidden cross-modal semantics and weak image-text relationships when modeling text and images.
Outcome:	The proposed model improves by up to 2.6 F1 score across five diverse social media datasets.

Sentiment Reasoning for Healthcare (2025.acl-industry)

Copied to clipboard

Khai-Nguyen Nguyen, Khai Le-Duc, Bach Phan Tat, Le Duy, Long Vo-Dang, Truong-Son Hy

Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need (2020.coling-main)

Challenge:	Sentiment Reasoning is an auxiliary task in sentiment analysis where the model predicts both the sentiment label and generates the rationale behind it based on the input transcript.
Approach:	They propose a task - Sentiment Reasoning - for both speech and textmodalities and propose 'multimodal multitask framework' . they propose to use a model that generates the rationale behind each predicted label and provides a rationale for model prediction with quality semantically comparable to humans.
Outcome:	The proposed task improves model transparency by providing rationale for model prediction with quality semantically comparable to humans while improving model’s classification performance.

Copied to clipboard

Shounak Paul, Pawan Goyal, Saptarshi Ghosh

Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation (2021.findings-acl)

Challenge:	Existing work on charge-side representations but not much effort has been made in improving fact-side models.
Approach:	They propose to use sentence-level charge labels as an auxiliary task coupled with the main task of document-level charging identification in a multi-task learning framework to improve fact-side representations.
Outcome:	The proposed model outperforms a large number of baselines on a document-level charge identification task.

Copied to clipboard

Shun-Po Chuang, Yung-Sung Chuang, Chih-Chiang Chang, Hung-yi Lee

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation (2025.acl-short)

Challenge:	Using connectionist temporal classification (CTC) for speech-to-text translation is counter-intuitive due to its monotonicity assumption.
Approach:	They propose to build a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC) their work shows transformer encoders can change the word order and points out the future research direction that needs to be explored more on non-Autoregressives speech translation.
Outcome:	The proposed model improves translation performance by using transformer encoders.

Copied to clipboard

Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman, Nanshu Wang, Tengyu Xu, Alexander Radovic, Eryk Helenowski, Arya Talebzadeh, Aditya Tayade, Sinong Wang, Shafiq Joty, Han Fang, Hao Ma

Reasoning

Challenge:	Existing methods for detecting hallucination in long-form tasks focus on limited domains or rely heavily on external fact-checking tools, which may not always be available.
Approach:	They propose a new paradigm that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection.
Outcome:	The proposed method outperforms existing methods for detecting hallucination in open-domain long-form generation and is more accurate than random guessing.

Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays (2022.naacl-main)

Copied to clipboard

Rahul Kumar, Sandeep Mathias, Sriparna Saha, Pushpak Bhattacharyya

Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Task (2021.findings-emnlp)

Challenge:	In automatic essay grading, essay traits are important for scoring the essay holistically . a single-task learning system gives the best results for scoring essays holistically and scoring essay traits.
Approach:	They propose a way to score essays using a multi-task learning approach . they compare the MTL-based BiLSTM system to a single-task Learning approach based on LSTMs and BiLStms .
Outcome:	The proposed system gives better results for scoring essay holistically and scoring essay traits.

Copied to clipboard

Yohan Lee

Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity (2020.coling-main)

Challenge:	Using large pre-trained language models for end-to-end TOD modeling has made significant progress on benchmarks . a paradigm of leveraging large pretrained models has shown promising results .
Approach:	They combine paradigm of leveraging large pre-trained language models with multi-task learning framework . their model achieves new state-of-the-art results with combined scores of 108.3 and 107.5 .
Outcome:	The proposed model achieves state-of-the-art results on multiWOZ 2.0 and MultiWOZ 2.1 . it also improves generalization capability through domain adaptation experiments in the few-shot setting.

Copied to clipboard

Anne Lauscher, Ivan Vulić, Edoardo Maria Ponti, Anna Korhonen, Goran Glavaš

Zero-shot Entity Linking with Less Data (2022.findings-naacl)

Challenge:	Unsupervised pretraining models encode only distributional knowledge encoded in text corpora, incorporated through language modeling objectives.
Approach:	They generalize a standard BERT model to a multi-task learning setting and integrate discrete knowledge on word-level semantic similarity into pretraining.
Outcome:	The proposed model outperforms the lexically blind “vanilla” model on several language understanding tasks.

Copied to clipboard

G P Shrivatsa Bhargav, Dinesh Khandelwal, Saswati Dana, Dinesh Garg, Pavan Kapanipathi, Salim Roukos, Alexander Gray, L Venkata Subramaniam

Zero-Shot and Few-Shot Stance Detection on Varied Topics via Conditional Generation (2023.acl-short)

Challenge:	Entity linking maps an entity mention in a natural language sentence to an entity in KB.
Approach:	They propose a neuro-symbolic, multi-task learning approach to bridge this gap by exploiting an auxiliary information about entity types.
Outcome:	The proposed approach achieves significantly higher performance on four different benchmark datasets when trained with just 0.01%, 0.1%, or 1% of the training data.

Copied to clipboard

Haoyang Wen, Alexander Hauptmann

Dialogue Coherence Assessment Without Explicit Dialogue Act Labels (2020.acl-main)

Challenge:	Existing work on stance detection focuses on in-domain or leave-out targets with only a few target choices.
Approach:	They propose to use a conditional generation framework to denoise from partially-filled templates to better utilize the semantics among input, label, and target texts.
Outcome:	The proposed method significantly outperforms strong baselines on VAST and achieves new state-of-the-art performance.

Copied to clipboard

Mohsen Mesgar, Sebastian Bücker, Iryna Gurevych

Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing (2021.findings-acl)

Challenge:	Recent dialogue coherence models use coherency features designed for monologue texts to represent utterances and then explicitly augment them with dialogue-relevant features, e.g., dialogue act labels.
Approach:	They propose a multi-task learning approach that uses dialogue act prediction to obtain informative utterance representations for coherence assessment.
Outcome:	The proposed model outperforms its strong competitors on the DailyDialogue corpus and performs on par with them on the SwitchBoard corpus for ranking dialogues concerning their coherence.

Copied to clipboard

Yitao Cai, Zhe Lin, Xiaojun Wan

Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance (2022.findings-emnlp)

Challenge:	Existing work on meaning representations for English and other languages finds that concepts in their predicted AMR graphs are less specific.
Approach:	They propose a cross-lingual AMR parser that can predict more precise concepts by translating translated texts and non-English texts.
Outcome:	The proposed model surpasses state-of-the-art parser by 10.6 points on Smatch F1 score.

Copied to clipboard

Abhishek Agarwal, Shanshan Xu, Matthias Grabmair

Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation (2021.naacl-main)

Challenge:	Summarizing legal decisions requires the expertise of law practitioners, which is time- and cost-intensive.
Approach:	They propose methods for extracting summarized legal decisions using limited expert annotated data.
Outcome:	The proposed models achieve ROUGE scores vis-à-vis expert extracted summaries that match inter-annotator comparisons.

Copied to clipboard

Hirofumi Inaguma, Tatsuya Kawahara, Shinji Watanabe

Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem (2022.findings-acl)

Challenge:	End-to-end speech translation models can be trained to leverage source text . however, since the input modalities are different, it is difficult to leverage the source text successfully.
Approach:	They propose to leverage source transcriptions via pre-training and joint training with ASR and NMT tasks.
Outcome:	The proposed model predicts paraphrased transcriptions as an auxiliary task with a single decoder.

Copied to clipboard

Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, Hamed Firooz

SynET: Synonym Expansion using Transitivity (2020.findings-emnlp)

Challenge:	Existing methods for entity linking do not use a knowledge base or candidate sets.
Approach:	They propose an autoregressive entity linking model that is trained with two auxiliary tasks and learns to re-rank generated samples at inference time.
Outcome:	The proposed model improves on two biomedical datasets and a news domain dataset without the use of a knowledge base or candidate sets.

Copied to clipboard

Jiale Yu, Yongliang Shen, Xinyin Ma, Chenghao Jia, Chen Chen, Weiming Lu

Challenge:	Existing approaches to find synonyms from text corpora are distributed and pattern based, but they suffer from low precision and low recall.
Approach:	They propose a task of synonym expansion using transitivity and propose auxiliary task to reduce the impact of noisy sentences.
Outcome:	The proposed approach reduces the impact of noisy sentences and reduces noise in a real-world dataset.

Why Don’t You Do It Right? Analysing Annotators’ Disagreement in Subjective Tasks (2023.eacl-main)

Copied to clipboard

Marta Sandri, Elisa Leonardelli, Sara Tonelli, Elisabetta Jezek

Text Classification

Challenge:	Disagreement can reflect different aspects of linguistic annotation, from annotators’ subjectivity to sloppiness or lack of context to interpret a text.
Approach:	They propose a taxonomy of possible reasons leading to annotators' disagreement in subjective tasks and manually label part of a Twitter dataset for offensive language detection in english following this taxonomies.
Outcome:	The proposed taxonomy of disagreements in linguistic datasets can be used to assess how accurate tweets belonging to different disagreement categories can be classified as offensive or not.

Flat Multi-modal Interaction Transformer for Named Entity Recognition (2022.coling-1)

Copied to clipboard

Junyu Lu, Dixiang Zhang, Jiaxing Zhang, Pingjian Zhang

Extracting Military Event Temporal Relations via Relative Event Time Prediction and Virtual Adversarial Training (2025.findings-naacl)

Challenge:	Named entity recognition (MNER) aims at identifying entity spans and recognizing their categories in social media posts with the aid of images.
Approach:	They propose to use sentences and general domain words to obtain visual cues to transform the fine-grained semantic representation of vision and text into a unified lattice structure and leverage entity boundary detection as an auxiliary task to alleviate visual bias.
Outcome:	The proposed method achieves state-of-the-art on two benchmark datasets.

Copied to clipboard

Jie Gong, Qiwang Hu

Robustness in NLP

Challenge:	Existing models for extracting event temporal relations typically compare the relative times of events directly, neglecting the contextual information between event pairs.
Approach:	They propose a temporal relationship extraction model based on relative event time prediction and virtual adversarial training, MFRV.
Outcome:	The proposed model can capture and infer temporal relationships and can be generalized by generating adversarial samples.

DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning (2025.findings-acl)

Copied to clipboard

Kang He, Yuzhe Ding, Haining Wang, Fei Li, Chong Teng, Donghong Ji

Context-Aware Answer Extraction in Question Answering (2020.emnlp-main)

Challenge:	Existing multimodal sentence representation learning methods focus on aligning images and text at a coarse level, resulting in cross-modal misalignment bias and intra-modal semantic divergence.
Approach:	They propose a dual-level alignment learning framework for multimodal sentence representation learning that promotes cross-modal and intra-modal alignment.
Outcome:	The proposed framework outperforms state-of-the-art methods on semantic textual similarity and transfer tasks on semantic similarity, ranking distillation and global intra-modal alignment learning.

Copied to clipboard

Yeon Seonwoo, Ji-Hoon Kim, Jung-Woo Ha, Alice Oh

Question Answering

Challenge:	Extractive QA models have shown promising performance in predicting the correct answer to a given question.
Approach:	They propose a BLANC-based context prediction task that learns the context prediction tasks.
Outcome:	The proposed model outperforms the state-of-the-art models on reading comprehension and hotpotQA.

LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations (2021.acl-long)

Copied to clipboard

Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu, Kai Yu

Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval (2021.findings-emnlp)

Challenge:	Existing methods to encode text-to-SQL data are node-centric and ignore semantics embedded in the topological structure of edges.
Approach:	They propose a Line Graph Enhanced Text-to-SQL model to mine relational features without constructing meta-paths.
Outcome:	The proposed model achieves state-of-the-art on the cross-domain text-to-SQL benchmark Spider at the time of writing.

Copied to clipboard

Yanmeng Wang, Jun Bai, Ye Wang, Jianfei Zhang, Wenge Rong, Zongcheng Ji, Shaojun Wang, Jing Xiao

Recursive Neural Structural Correspondence Network for Cross-domain Aspect and Opinion Co-Extraction (P18-1)

Challenge:	Existing approaches to solve question answering (QA) problems are limited by the need for text generation and answer retrieval.
Approach:	They propose to introduce QA interaction features in scoring function but at the cost of low efficiency in inference stage.
Outcome:	The proposed framework significantly outperforms the state-of-the-art method on multiple answer retrieval datasets.

Copied to clipboard

Wenya Wang, Sinno Jialin Pan

Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning (2021.naacl-main)

Challenge:	supervised learning methods have been used for fine-grained opinion analysis but lack of labeled data hinders learning . authors develop a recursive neural network that could reduce domain shift in word level . a recent paper shows that unsupervised methods fail to adapt well across domains .
Approach:	They propose a supervised neural network that reduces domain shift effectively in word level . they treat these relations as invariant "pivot information" across domains to build structural correspondences .
Outcome:	The proposed model reduces domain shift effectively in word level through syntactic relations . it can be used to predict the relation between two adjacent words in the dependency tree .

Copied to clipboard

Tommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, Massimo Poesio

Efficient Strategies for Hierarchical Text Classification: External Knowledge and Auxiliary Tasks (2020.acl-main)

Challenge:	Prior work shows that disagreement between annotators can be useful in training models.
Approach:	They propose to use disagreements as an auxiliary task in a multi-task neural network to incorporate disagreements into models.
Outcome:	The proposed method significantly improves performance on NLP tasks beyond the standard approach and prior work.

Copied to clipboard

Kervy Rivas Rojas, Gina Bustamante, Arturo Oncevay, Marco Antonio Sobrevilla Cabezudo

Information Retrieval

Challenge:	Hierarchical text classification is a complex task that requires extended training time and a large number of parameters.
Approach:	They propose a top-up-classification task using dictionaries and auxiliary task from external dictionary definitions.
Outcome:	The proposed method outperforms previous studies using a reduced number of parameters in two well-known English datasets.

Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions (2020.acl-main)

Copied to clipboard

Hannah Craighead, Andrew Caines, Paula Buttery, Helen Yannakoudakis

Speech & Audio in NLP

Challenge:	a growing demand for the ability to communicate in English means automated tutoring and assessment systems are becoming more popular.
Approach:	They propose to use automatic speech recognition transcripts to grade spontaneous speech based on textual features.
Outcome:	The proposed system improves on a transformer encoder with native language identification as an auxiliary task.

MUSER: MUltimodal Stress detection using Emotion Recognition as an Auxiliary Task (2021.naacl-main)

Copied to clipboard

Yiqun Yao, Michalis Papakostas, Mihai Burzo, Mohamed Abouelenien, Rada Mihalcea

Detecting Optimism in Tweets using Knowledge Distillation and Linguistic Analysis of Optimism (2022.lrec-1)

Challenge:	Existing methods to detect stress have not explored the inter-dependence between emotion and stress.
Approach:	They propose a transformer-based model architecture and a novel multi-task learning algorithm with speed-based dynamic sampling strategy to improve stress detection.
Outcome:	The proposed model is effective with internal and external auxiliary tasks and achieves state-of-the-art results.

Copied to clipboard

Ștefan Cobeli, Ioan-Bogdan Iordache, Shweta Yadav, Cornelia Caragea, Liviu P. Dinu, Dragoș Iliescu

Predicting Discourse Structure using Distant Supervision from Sentiment (D19-1)

Challenge:	a recent study has established sentiment analysis as an alluring problem, but many feelings are left unexplored.
Approach:	They propose a framework to learn the polarity of emotions from Twitter posts . they compare optimism detection with sentiment analysis and hate speech detection .
Outcome:	The proposed framework differs between optimistic and pessimistic users on the Optimism/Pessimism Twitter dataset.

Copied to clipboard

Patrick Huber, Giuseppe Carenini

Selecting Stickers in Open-Domain Dialogue through Multitask Learning (2022.findings-acl)

Challenge:	Discourse parsing is a fundamental NLP task known to enhance key downstream tasks, such as sentiment analysis, text classification and summarization.
Approach:	They propose a method that uses document supervision to generate abundant data for RST-style discourse structure prediction by using an optimal CKY-style tree generation algorithm.
Outcome:	The proposed approach performs well on the more difficult task of inter-domain discourse structure prediction, but it does not match the performance of a parser trained and tested on the same dataset.

Copied to clipboard

Zhexin Zhang, Yeshuang Zhu, Zhengcong Fei, Jinchao Zhang, Jie Zhou

“Be nice to your wife! The restaurants are closed”: Can Gender Stereotype Detection Improve Sexism Classification? (2021.findings-emnlp)

Challenge:	Existing methods to select appropriate stickers in open-domain dialogues have not been explored.
Approach:	They propose a multitask learning method consisting of three auxiliary tasks to combine multimodal information to enhance the understanding of dialogue history, emotion and semantic meaning of stickers.
Outcome:	The proposed model can combine multimodal information and achieve significantly higher accuracy over strong baselines.

Copied to clipboard

Patricia Chiril, Farah Benamara, Véronique Moriceau

Information Retrieval

Challenge:	a new study examines the impact of gender stereotype detection on sexism classification . GS is defined as "pictures in our heads" and is used to describe social group members .
Approach:	They propose to use tweets as a dataset to detect sexist hate speech . they propose a method for data augmentation based on sentence similarity with external datasets .
Outcome:	The proposed method detects sexist hate speech in tweets and then uses it for sexism classification.

Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations (2021.findings-emnlp)

Copied to clipboard

Yunhe Xie, Kailai Yang, Chengjie Sun, Bingquan Liu, Zhenzhou Ji

ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation (2021.findings-acl)

Challenge:	Emotion Recognition in Conversation models neglect direct utterance-knowledge interaction and use emotion-indirect auxiliary tasks to augment semantic information.
Approach:	They propose a Knowledge-Interactive Network with sentiment polarity intensity-aware multi-task learning which leverages both commonsense knowledge and sentiment lexicon to augment semantic information.
Outcome:	The proposed model shows 1.04% performance improvement over the state-of-the-art model on the IEMOCAP dataset.

Copied to clipboard

Kaushal Kumar Maurya, Maunendra Sankar Desarkar, Yoshinobu Kano, Kumari Deepshikha

Low-Resource NLP

Challenge:	Recent advances in NLP focus on large annotated training data.
Approach:	They propose an unsupervised framework that does not use parallel or pseudo-parallel/back-translated data.
Outcome:	The proposed framework does not use parallel or pseudo-parallel/back-translated data.

Text Augmentation in a Multi-Task View (2021.eacl-main)

Copied to clipboard

Jason Wei, Chengyu Huang, Shiqi Xu, Soroush Vosoughi

Low-Resource NLP

Challenge:	a multi-task view of data augmentation allows for a more robust performance than traditional augmentation.
Approach:	They propose a multi-task view of data augmentation where original and augmented samples are weighted substantively during training.
Outcome:	The proposed model improves on three benchmark text classification datasets.

How to disagree well: Investigating the dispute tactics used on Wikipedia (2022.emnlp-main)

Copied to clipboard

Christine De Kock, Andreas Vlachos

Challenge:	Disagreements are often studied from the perspective of toxicity or analysing argument structure.
Approach:	They propose a dispute tactics framework which unifies both perspectives . they annotate 213 disagreements from Wikipedia Talk pages .
Outcome:	The proposed framework can be used to predict disagreements with a transformer-based model.

2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition (2023.findings-emnlp)

Copied to clipboard

Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan Gao, Shusen Wang, Yao Hu, Yiqing Lin

Low-Resource NLP

Challenge:	Named Entity Recognition (NER) tasks are a fundamental task of natural language processing (NLP).
Approach:	They propose a text-to-text framework for Few-Shot Named Entity Recognition (NER) that employs instruction finetuning and auxiliary tasks to enhance the model's understanding of entity types in the overall semantic context of a sentence.
Outcome:	The proposed framework outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art NER algorithms.

Scientific Paper Extractive Summarization Enhanced by Citation Graphs (2022.emnlp-main)

Copied to clipboard

Xiuying Chen, Mingzhe Li, Shen Gao, Rui Yan, Xin Gao, Xiangliang Zhang

Visual Cues and Error Correction for Translation Robustness (2021.findings-emnlp)

Challenge:	citation graphs can be used to extract scientific papers under different conditions.
Approach:	They propose a multi-granularity unsupervised summarization model that fine tunes a pre-trained encoder model on the citation graph by link prediction tasks.
Outcome:	The proposed model outperforms baseline models on a public benchmark dataset.

Copied to clipboard

Zhenhao Li, Marek Rei, Lucia Specia

Multilinguality

Challenge:	Existing robustness techniques fail when faced with unseen types of noise and their performance degrades on clean texts.
Approach:	They propose visual context to improve translation robustness for noisy texts . they also propose an error correction training regime that can be used as an auxiliary task .
Outcome:	The proposed training regime improves translation robustness on noisy texts while maintaining translation quality on clean texts.

ChatASU: Evoking LLM’s Reflexion to Truly Understand Aspect Sentiment in Dialogues (2024.lrec-main)

Copied to clipboard

Yiding Liu, Jingjing Wang, Jiamin Luo, Tao Zeng, Guodong Zhou

Natural Language Interfaces

Challenge:	Existing studies on interactive ASU ignore the coreference issue for opinion targets while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance.
Approach:	They propose a Chat-based Aspect Sentiment Understanding task that integrates various NLP tasks with the chat paradigm and propose 'trusted self-reflexion' approach with ChatGLM as backbone to address aspect coreference issue.
Outcome:	The proposed task outperforms state-of-the-art baselines and shows that it is highly effective.

HLDC: Hindi Legal Documents Corpus (2022.findings-acl)

Copied to clipboard

Arnav Kapoor, Mudit Dhawan, Anmol Goel, Arjun T H, Akshala Bhatnagar, Vibhu Agrawal, Amul Agrawal, Arnab Bhattacharya, Ponnurangam Kumaraguru, Ashutosh Modi

Challenge:	Existing systems that process legal documents are lacking high-quality corpora in low resource languages such as Hindi.
Approach:	They propose a Hindi Legal Documents Corpus (HLDC) that contains 900K legal documents in Hindi.
Outcome:	The proposed model is based on a corpus of more than 900K legal documents in Hindi.

Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity (2022.emnlp-main)

Copied to clipboard

Jiahao Li, Quan Wang, Zhendong Mao, Junbo Guo, Yanyan Yang, Yongdong Zhang

Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation (2021.naacl-main)

Challenge:	Chinese spelling check (CSC) is a fundamental NLP task that detects and corrects spelling errors in Chinese texts.
Approach:	They propose an auxiliary task of Chinese pronunciation prediction to improve CSC . they propose adaptive weighting schemes and a delicate correction strategy .
Outcome:	The proposed auxiliary task improves Chinese pronunciation prediction on three benchmarks.

Copied to clipboard

Yongchang Hao, Shilin He, Wenxiang Jiao, Zhaopeng Tu, Michael Lyu, Xing Wang

Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task (2021.acl-long)

Challenge:	Existing non-autoregressive machine translation models have shown significant inference speedup but suffer from inferior translation accuracy.
Approach:	They propose to use AT as an auxiliary task to transfer AT knowledge to NAT models by knowledge distillation.
Outcome:	The proposed method achieves significant improvements over baseline non-Autoregressive machine translation models on WMT14 En-De and WMT16 En-Ro datasets.

Copied to clipboard

Yun Tang, Juan Pino, Xian Li, Changhan Wang, Dmitriy Genzel

Speech & Audio in NLP

Challenge:	Pretraining and multitask learning are widely used to improve the speech translation performance.
Approach:	They propose to train a speech translation model along with an auxiliary text translation task.
Outcome:	The proposed method improves translation quality by more than 2 BLEU over a strong baseline and achieves state-of-the-art results on the MuST-C English-German, English-French and English-Spanish language pairs.

Multi-Task Learning with Language Modeling for Question Generation (D19-1)

Copied to clipboard

Wenjie Zhou, Minghua Zhang, Yunfang Wu

AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning (N19-1)

Challenge:	Existing work on answer-aware questions generates a sentence and answer span as input . previous work on QG was mainly tackled by rule-based approach and neural-based one .
Approach:	They propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure.
Outcome:	The proposed model improves on SQuAD and MARCO datasets and human evaluation proves it.

Copied to clipboard

Han Guo, Ramakanth Pasunuru, Mohit Bansal

Generalizable and Explainable Dialogue Generation via Explicit Action Learning (2020.findings-emnlp)

Challenge:	Multi-task learning is an inductive transfer mechanism that leverages information from related tasks to improve the primary model's generalization performance.
Approach:	They propose a multitask learning pipeline that finds relevant auxiliary tasks and learns their mixing ratio.
Outcome:	The proposed model can find relevant auxiliary tasks and learn their mixing ratio . the proposed model achieves significant performance boosts on several primary tasks .

Copied to clipboard

Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang

HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations (2020.coling-main)

Challenge:	Conditioned response generation for task-oriented dialogues implicitly optimizes task completion and language quality.
Approach:	They propose to learn natural language actions that represent utterances as a span of words.
Outcome:	The proposed approach outperforms latent action baselines on a multi-domain dataset.

Copied to clipboard

Jingye Li, Donghong Ji, Fei Li, Meishan Zhang, Yijiang Liu

Learning Task Sampling Policy for Multitask Learning (2021.findings-emnlp)

Challenge:	Emotion detection in conversations is to detect the emotion for each utterance in conversations that have multiple speakers.
Approach:	They propose a transformer-based context- and speaker-sensitive model for EDC . they utilize a low-level transformer to generate local utterance representations .
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark datasets.

Copied to clipboard

Dhanasekar Sundararaman, Henry Tsai, Kuang-Huei Lee, Iulia Turc, Lawrence Carin

Persian Natural Language Inference: A Meta-learning Approach (2022.coling-1)

Challenge:	Existing methods to train multi-task models with auxiliary tasks are limited by the number of combinations and the importance of each auxiliary task is not known a priori.
Approach:	They propose a search method that automatically assigns importance weights to auxiliary tasks to improve the target task quality.
Outcome:	The proposed method outperforms uniform sampling and the corresponding single-task baseline on XNLI and GLUE.

Copied to clipboard

Heydar Soudani, Mohammad Hassan Mojab, Hamid Beigy

On Losses for Modern Language Models (2020.emnlp-main)

Challenge:	In general, shared representations are learned separately, either across tasks or across languages.
Approach:	They propose a meta-learning approach for inferring natural language in Persian . they use different task information or other language information to form additional high-quality tasks .
Outcome:	The proposed method outperforms the baseline approach, improving accuracy by roughly six percent.

Copied to clipboard

Stéphane Aroca-Ouellette, Frank Rudzicz

Learning Constraints and Descriptive Segmentation for Subevent Detection (2021.emnlp-main)

Challenge:	Devlin et al. ( 2018) released a transformer network (BERT) pre-training over two tasks: masked language modelling (MLM) and next sentence prediction (NSP).
Approach:	They clarify NSP's effect on BERT pre-training and explore ways to include multiple tasks into pre-train.
Outcome:	The proposed framework outperforms BERTBase on the GLUE benchmark using fewer than a quarter of training tokens.

Copied to clipboard

Haoyu Wang, Hongming Zhang, Muhao Chen, Dan Roth

Challenge:	Event mentions in text correspond to real-world events of varying degrees of granularity . task of subevent detection aims to resolve this granulem issue by recognizing membership of events .
Approach:	They propose a task of event-based text segmentation as an auxiliary task to improve learning for subevent detection.
Outcome:	The proposed method outperforms baseline methods on subevent detection, HiEve and IC datasets while achieving decent performance on EventSeg prediction.

WebIE: Faithful and Robust Information Extraction on the Web (2023.acl-long)

Copied to clipboard

Chenxi Whitehouse, Clara Vania, Alham Fikri Aji, Christos Christodoulopoulos, Andrea Pierleoni

Robustness in NLP

Challenge:	Existing closed IE datasets are built using Wikipedia, but they have limitations when applied to web domains.
Approach:	They propose to annotate 25K triples from WebIE through crowdsourcing and introduce mWebIE, a translation of the annotated set in four other languages.
Outcome:	The proposed model trains on 1.6M sentences from the English Common Crawl corpus and includes negative examples to better reflect the data on the web.

Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings (D18-1)

Copied to clipboard

Shafiq Joty, Lluís Màrquez, Preslav Nakov

Representation Learning

Challenge:	Stack-Overflow, Quora, and Yahoo! Answers forums are not moderated, which results in noisy and redundant content.
Approach:	They use deep neural networks to learn meaningful task-specific embeddings . they incorporate the embeddables into a conditional random field model .
Outcome:	The proposed task improves significantly across evaluation metrics.

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026.acl-long)

Copied to clipboard

Kaiwen Wei, Kejun he, Xiaomian Kang, Jie Zhang, null Ymyang, Li Jin, Zhenyang Li, Jiang Zhong, Richard He Bai, Junnan Zhu

Position Offset Label Prediction for Grammatical Error Correction (2022.coling-1)

Challenge:	Generative recommendation models inherently bias towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents.
Approach:	They propose a training framework that shifts the objective from simple next-step prediction to deep comprehension of history by entropy-guided masking policy and a curriculum learning scheduler to enhance the framework.
Outcome:	The proposed framework outperforms state-of-the-art generative models on three public datasets and shows that it is more accurate than current models.

Copied to clipboard

Xiuyu Wu, Jingsong Yu, Xu Sun, Yunfang Wu

Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering (2021.emnlp-main)

Challenge:	Experimental results show that our proposed POL-Pc framework improves baseline models and yields consistent performance gain over various data augmentation methods.
Approach:	They propose a position offset label prediction subtask to integrate correction editing operations into a unified framework.
Outcome:	The proposed model outperforms baseline models on Chinese, English and Japanese datasets by a wide margin.

Copied to clipboard

Jihyung Kil, Cheng Zhang, Dong Xuan, Wei-Lun Chao

Visual Data in NLP

Challenge:	Existing methods address this issue by introducing an auxiliary task such as visual grounding, cycle consistency, or debiasing.
Approach:	They propose a data augmentation pipeline to turn “known” knowledge into training examples for VQA.
Outcome:	The proposed model can handle multi-modal information and is based on human-annotated examples.

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

What can we learn from Semantic Tagging? (D18-1)

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.

Copied to clipboard

Mostafa Abdou, Artur Kulmizev, Vinit Ravishankar, Lasha Abzianidze, Johan Bos

Enhancing Knowledge Selection via Multi-level Document Semantic Graph (2024.lrec-main)

Challenge:	a recent study shows that multi-task learning improves performance of NLP tasks by exploiting similarities between tasks.
Approach:	They employ semantic tagging as an auxiliary task for three NLP tasks . they compare full neural network sharing, partial neural network shared and learning what to share .
Outcome:	The proposed model improves for part-of-speech tagging, universal dependency parsing and natural language inference.

Copied to clipboard

Haoran Zhang, Tan Yongmei

Structured Data in NLP

Challenge:	Existing methods view knowledge selection as a sentence matching or classification. Existing techniques can’t capture the semantic relationships within complex documents.
Approach:	They propose a method that can construct multi-level document semantic graph from the grounding document and store semantic relationships within the documents effectively.
Outcome:	The proposed method can store semantic relationships within documents effectively and efficiently and achieve state-of-the-art results on public datasets.

Multi-resolution Annotations for Emoji Prediction (2020.emnlp-main)

Copied to clipboard

Weicheng Ma, Ruibo Liu, Lili Wang, Soroush Vosoughi

Visual Data in NLP

Challenge:	Emojis are able to express various linguistic components, such as emotions, sentiments, events, etc. emojis have the merit of preserving information more densely, compared to words, argues a new study.
Approach:	They propose to use passage-level and aspect-level emoji annotations to predict the proper emmojis associated with text.
Outcome:	The proposed method is heuristically generated and validated with a pre-trained BERT model.

How to Ask Good Questions? Try to Leverage Paraphrases (2020.acl-main)

Copied to clipboard

Xin Jia, Wenjie Zhou, Xu Sun, Yunfang Wu

Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness (2024.findings-acl)

Challenge:	Existing methods to generate human-like questions rely on paraphrases to generate good questions.
Approach:	They propose to integrate paraphrase knowledge into question generation to generate human-like questions by combining paraphrases with a back-translation method.
Outcome:	The proposed model achieves obvious performance gain over several strong baselines and human evaluation validates that it can ask questions of high quality by leveraging paraphrase knowledge.

Copied to clipboard

Maximilian Spliethöver, Sai Nikhil Menon, Henning Wachsmuth

A New Direction in Stance Detection: Target-Stance Extraction in the Wild (2023.acl-long)

Challenge:	Existing studies have studied dialect-related fairness for aspects like hate speech, but other aspects of biased language remain unexplored.
Approach:	They propose a multitask learning approach that models dialect language as an auxiliary task to incorporate syntactic and lexical variations.
Outcome:	The proposed approach improves dialect learning and detects biases more reliably.

Copied to clipboard

Yingjie Li, Krishna Garg, Cornelia Caragea

Hierarchical Multi-Label Classification of Scientific Documents (2022.emnlp-main)

Challenge:	Existing methods for stance detection assume that the target is known in advance . Existing tasks use implicit mentions in the source text and are infeasible to have manual annotations at a large scale.
Approach:	They propose a task Target-Stance Extraction that aims to extract the (target, stance) pair from social media texts.
Outcome:	The proposed task can facilitate future research in the field of stance detection.

Copied to clipboard

Mobashir Sadat, Cornelia Caragea

Information Retrieval

Challenge:	Automated topic classification is a useful tool for managing scientific documents in a digital collection.
Approach:	They propose a hierarchical multi-label text classification dataset with keyword labeling as an auxiliary task.
Outcome:	The proposed model achieves a Macro-F1 score of 34.57% and is publicly available.

Modeling Long Context for Task-Oriented Dialogue State Generation (2020.acl-main)

Copied to clipboard

Jun Quan, Deyi Xiong

Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction Graph (2023.findings-acl)

Challenge:	Existing approaches to dialogue state tracking are limited to scenarios with infinite slot values and prediction of unseen slot values.
Approach:	They propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation.
Outcome:	The proposed model achieves state-of-the-art accuracy on the MultiWOZ 2.0 dataset.

Copied to clipboard

Ruili Pu, Yang Li, Suge Wang, Deyu Li, Jianxing Zheng, Jian Liao

Structured Data in NLP

Challenge:	Existing methods for event causality identification (ECI) do not consider event causal label information and interaction information between event pairs.
Approach:	They propose a framework to enrich the representation of event pairs by introducing the event causal label information and the interaction information between event pairs.
Outcome:	The proposed framework outperforms state-of-the-art methods on two benchmark datasets.

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

Copied to clipboard

Yingjie Li, Cornelia Caragea

Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies (2020.emnlp-main)

Challenge:	Recent studies show improvements in stance detection by using attention mechanism or sentiment information.
Approach:	They propose a multi-task framework that incorporates attention mechanism and takes sentiment classification as an auxiliary task.
Outcome:	The proposed model outperforms state-of-the-art deep learning methods on the SemEval-2016 dataset.

Copied to clipboard

Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

Multilinguality

Challenge:	Existing methods for developing broad-coverage semantic dependency parsers for languages without semantically annotated data are limited to English, Czech and Chinese.
Approach:	They propose a multitask learning framework coupled with annotation projection to build broad-coverage semantic dependency parsers for languages without annotated resources.
Outcome:	The proposed model improves labeled F1 score on multitask tasks from English to Czech compared to baseline models .

GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding (2025.acl-long)

Copied to clipboard

Ziyin Zhang, Hang Yu, Sage Lee, Peng Di, Jianguo Li, Rui Wang

Complementary Learning of Aspect Terms for Aspect-based Sentiment Analysis (2022.lrec-1)

Challenge:	Programming languages have rich semantics that are represented by graphs and not available from the surface form of source code.
Approach:	They propose to use graph neural networks and cross-modal alignment technologies to inject structural information of code into LLMs as an auxiliary task during finetuning.
Outcome:	The proposed framework improves on five code tasks with six different baseline LLMs, while incurring no cost at inference time.

Copied to clipboard

Han Qin, Yuanhe Tian, Fei Xia, Yan Song

TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition (2023.findings-acl)

Challenge:	Existing ABSA models do not pay attention to aspect terms and their contexts . a discriminator is introduced to improve ABSA, allowing for better understanding of aspect terms .
Approach:	They propose to improve ABSA by complementary learning of aspect terms . they explicitly recover aspect terms from each input sentence to better understand aspects .
Outcome:	The proposed approach improves ABSA on five widely used English benchmark datasets.

Copied to clipboard

Wei Xiang, Chao Liang, Bang Wang

Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction (2021.emnlp-main)

Challenge:	Existing prompt learning models for IDRR use multiple-prompt decisions from three different yet much similar connective prediction templates.
Approach:	They propose to fuse three related tasks to fuse the learned features of auxiliary tasks to create a prompt learning model that can be used to boost the main task.
Outcome:	The proposed model outperforms the ConnPrompt in the training phase and in the testing phase.

Copied to clipboard

Haoyang Wen, Heng Ji

PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning (2026.findings-acl)

Challenge:	Existing methods for event-event temporal relation extraction are sparse on event-time information.
Approach:	They propose a model for event-event temporal relation classification and an auxiliary task, relative event time prediction, which predicts the event time as real numbers.
Outcome:	The proposed model significantly improves the RoBERTa-based baseline and achieves state-of-the-art performance on MATRES dataset.

Copied to clipboard

Yunzhi Shen, Hao Zhou, Xin Huang, Xue Han, Junlan Feng, Shujian Huang

Document-Level Relation Extraction with Global Relations and Entity Pair Reasoning (2025.findings-acl)

Challenge:	Reinforcement learning (RL) has shown strong promise for LLM-based machine translation . however, translation-oriented RL remains challenged by high-variance policy gradients induced by Monte Carlo baselines and large trajectory space that favors global exploration over fine-grained local optimization.
Approach:	They propose a two-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization.
Outcome:	The proposed framework supports global exploration and fine-grained optimization while supporting global exploration.

Copied to clipboard

Fu Zhang, Yi Yan, Jingwei Cheng

Non-Essential Is NEcessary: Order-agnostic Multi-hop Question Generation (2024.lrec-main)

Challenge:	Existing document-level relation extraction models focus on individual entity pairs, limiting their ability to handle complex reasoning tasks.
Approach:	They propose a document-level relation extraction framework based on global relations and entity pair reasoning that captures fine-grained interactions between entity pairs.
Outcome:	The proposed framework outperforms existing models on widely-used datasets.

Copied to clipboard

Kyungho Kim, Seongmin Park, Junseo Lee, Jihwa Lee

Phonotactic Complexity across Dialects (2024.lrec-main)

Challenge:	Existing multi-hop question generation methods treat answer-irrelevant documents as non-essential and remove them as impurities, which can lead to a decrease in model performance.
Approach:	They propose a task which leverages non-essential data in the training phase to create a robust model and extract the consistent embeddings in real-world inference environments.
Outcome:	The proposed model can perform ranker and generator without external modules and achieves state-of-the-art on a hotpotQA dataset.

Copied to clipboard

Ryan Soh-Eun Shim, Kalvin Chang, David R. Mortensen

SGCM: Salience-Guided Context Modeling for Question Generation (2024.lrec-main)

Challenge:	Recent studies show a moderate negative correlation between phonotactic complexity and word length in 106 languages.
Approach:	They propose to use a phone-level language model to measure phonotactic complexity . they find a tradeoff between word length and phonomactic complex .
Outcome:	The proposed model shows that low phonotactic complexity dialects concentrate around capital regions.

Copied to clipboard

Chuyao Ding, Yu Hong, Jianmin Yao

ToNER: Type-oriented Named Entity Recognition with Generative Language Model (2024.lrec-main)

Challenge:	Identifying relevant sentences to answers is crucial for reasoning the possible questions before generation.
Approach:	They propose a salience-guided approach to enhance Paragraph-level Question Generation by identifying salient sentences that manifest relevance.
Outcome:	The proposed approach achieves Rouge-L, BLEU4, BERTScore, Q-BLUE-3 and F1-scores compared to baseline on FairytaleQA.

Copied to clipboard

Guochao Jiang, Ziqin Luo, Yuchen Shi, Dixuan Wang, Jiaqing Liang, Deqing Yang