Papers with multitask learning
MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore (2025.acl-demo)
Copied to clipboard
Yingxu He, Zhuohan Liu, Geyu Lin, Shuo Sun, Bin Wang, Wenyu Zhang, Xunlong Zou, Nancy F. Chen, AiTi Aw
| Challenge: | MERaLiON-AudioLLM is the first general-purpose audio-based large language model for multitask learning. |
| Approach: | They introduce MERaLiON-AudioLLM, a general-purpose audio-based large language model for multitask learning with a focus on Singlish understanding. |
| Outcome: | The proposed model exhibits strong generalization across a diverse set of tasks . it is a leading solution for region-specific AI applications. |
Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factor (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing models to classify rumors have low precision and are time consuming. |
| Approach: | They propose a multiloss hierarchical biLSTM model with an attenuation factor that can extract deep information from limited quantities of text. |
| Outcome: | The proposed model can extract deep information from limited quantities of text. |
Start Simple: Progressive Difficulty Multitask Learning (2024.naacl-srw)
Copied to clipboard
| Challenge: | a novel neural network training strategy that trains neural networks using subtasks of progressive difficulty is proposed . this strategy could help us understand how neural networks learn, authors say . |
| Approach: | They propose a multitask learning strategy that employs progressive difficulty subtasks to train neural networks. |
| Outcome: | The proposed strategy can improve model performance across a range of NLP tasks and data sets. |
Statistical Deficiency for Task Inclusion Estimation (2025.acl-long)
Copied to clipboard
Loïc Fosse, Frederic Bechet, Benoit Favre, Géraldine Damnati, Gwénolé Lecorvé, Maxime Darrin, Philippe Formont, Pablo Piantanida
| Challenge: | Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models. |
| Approach: | They propose a theoretically grounded setup to define the notion of task and compute the inclusion between two tasks from a statistical deficiency point of view. |
| Outcome: | The proposed model estimates the degree of inclusion between tasks on synthetic data and reconstructs the classic NLP pipeline. |
Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling (P19-3)
Copied to clipboard
Vighnesh Leonardo Shiv, Chris Quirk, Anshuman Suri, Xiang Gao, Khuram Shahid, Nithya Govindarajan, Yizhe Zhang, Jianfeng Gao, Michel Galley, Chris Brockett, Tulasi Menon, Bill Dolan
| Challenge: | upcoming open-source natural language processing repository aims to train conversational agents for multi-turn situations. |
| Approach: | They present the Intelligent Conversation Engine: Code and Pre-trained Systems (ICECAPS) the framework wraps TensorFlow functionality in a modular component-based architecture. |
| Outcome: | The Intelligent Conversation Engine: Code and Pre-trained Systems (ICECAPS) is an open-source natural language processing repository. |
A Boundary-aware Neural Model for Nested Named Entity Recognition (D19-1)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition ignore nested entities . a boundary-aware neural model can locate entities precisely by detecting boundaries . |
| Approach: | They propose a boundary-aware neural model for nested named entity recognition which leverages entity boundaries to predict entity categorical labels. |
| Outcome: | The proposed model outperforms state-of-the-art methods on GENIA dataset . it captures dependencies of entity boundaries and categorical labels, which helps to improve identifying entities. |
Multitask Parsing Across Semantic Representations (P18-1)
Copied to clipboard
| Challenge: | UCCA parsing is a test case for multitask learning, with auxiliary tasks AMR, SDP and Universal Dependencies (UD) . Semantic parsers have arguably yet to reach their full potential due to the limited amount of semantically annotated training data. |
| Approach: | They propose a general transition-based parser that can parse UCCA, AMR, SDP and Universal Dependencies (UD) they use a transition-driven learning architecture and a uniform transition-basic learning architecture to train the parsers. |
| Outcome: | The proposed parser improves UCCA, AMR, SDP and Universal Dependencies (UD) parsing over training in English, German and French. |
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
| 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 . |
Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent advances apply artificial intelligence to predict clinical events or infer the probable diagnosis for clinical decision support. |
| Approach: | They propose a hypernetwork-based approach that generates task-conditioned parameters and coefficients of multitask prediction heads to learn task-specific prediction and balance the multitask learning. |
| Outcome: | Experiments on clinical notes from the real-world MIMIC database show that the proposed model can achieve better performance than baselines and improve zero-shot prediction on unseen diagnoses. |
ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning (2023.acl-long)
Copied to clipboard
| Challenge: | Pretraining has been shown to scale well with compute, data size and data diversity. |
| Approach: | They propose a method that provides benefits of multitask learning but leverages distributed computation . they propose 'coldfusion' can create synergistic loop where finetuned models can be "recycled" |
| Outcome: | The proposed method outperforms RoBERTa and previous multitask models on 35 datasets. |
Exploring Multitask Learning for Low-Resource Abstractive Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work shows that training text encoders using data from multiple tasks helps to produce an encoder that can be used in numerous downstream tasks with minimal fine-tuning. |
| Approach: | They incorporate four different tasks to improve abstractive summarization performance . they use a pretrained BERT model and train all tasks using a small-scale training corpus . |
| Outcome: | The proposed model outperforms a model trained in a multitask setting with no additional summarization data. |
“Laughing at you or with you”: The Role of Sarcasm in Shaping the Disagreement Space (2021.eacl-main)
Copied to clipboard
| Challenge: | Detecting arguments in online interactions is useful to understand how conflicts arise and get resolved. |
| Approach: | They propose to use a corpus annotated with argumentative moves and sarcasm to model sarcastic relationships using deep learning architectures. |
| Outcome: | The proposed setup improves the argumentative relation classification task using deep learning architectures. |
Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling (P19-1)
Copied to clipboard
| Challenge: | Morphological tagging is challenging for morphologically rich languages due to the large combined target space and the need for more training data to minimize model sparsity. |
| Approach: | They propose to use multitask learning and adversarial training to address morphological richness and dialectal variations in the context of full morphology. |
| Outcome: | The proposed model achieves state-of-the-art for two dialectal variants: Modern Standard Arabic (high-resource “dialect”) and Egyptian Arabic (low-resourced dialect). |
Neural Multitask Learning for Simile Recognition (D18-1)
Copied to clipboard
| Challenge: | Simile is a special type of metaphor, where comparators such as like and as are used to compare two objects. |
| Approach: | They propose a neural network framework for simile sentence classification, simile component extraction and language modeling. |
| Outcome: | The proposed framework outperforms rule-based and feature-based approaches in simile sentence classification and simile component extraction tasks. |
ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs (2022.findings-naacl)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations. |
| Approach: | They propose to use auxiliary tasks which are semantically or formally related to enhance AMR parsing. |
| Outcome: | The proposed method achieves state-of-the-art performance on benchmarks especially in topology-related scores. |
MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling (2023.acl-long)
Copied to clipboard
| Challenge: | Using publicly available materials science text data, we construct a benchmark for evaluating the performance of natural language processing (NLP) models on materials science texts. |
| Approach: | They propose a natural language benchmark for evaluating the performance of natural language processing (NLP) models on materials science text. |
| Outcome: | The proposed model outperforms BERT-based models on scientific text and a model pretrained on materials science journals. |
FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent model-based reference-free metrics for open-domain dialogue evaluation lack correlations with human judgment and poor interpretability. |
| Approach: | They propose a multi-dimensional dialogue-level metric with three sub-metrics targeting a specific dimension. |
| Outcome: | The proposed metric outperforms existing models and sub-metrics in three high-quality dialogue evaluation benchmarks. |
Reinforced Multi-task Approach for Multi-hop Question Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Empirical evaluation shows our model to outperform the single-hop question generation models on both automatic evaluation metrics such as BLEU, METEOR, and ROUGE and human evaluation metrics for quality and coverage of the generated questions. |
| Approach: | They propose a question-aware reward function to maximize the utilization of supporting facts in the context. |
| Outcome: | The proposed model outperforms single-hop neural question generation models on automatic evaluation metrics and human evaluation metrics for quality and coverage of the generated questions. |
Unified Automated Essay Scoring and Grammatical Error Correction (2025.findings-naacl)
Copied to clipboard
| Challenge: | a new study explores the integration of automated writing evaluation and grammatical error correction through multitask learning. |
| Approach: | They propose a system that integrates automated writing evaluation and grammatical error correction through multitask learning by leveraging a shared learning framework. |
| Outcome: | The proposed system outperforms models trained on AWE and GEC, the authors show . their study demonstrates that the proposed system improves writing assessment accuracy and accuracy . |
BPM_MT: Enhanced Backchannel Prediction Model using Multi-Task Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Backchannel (BC) is a short and quick reaction signal of a listener to a speaker's utterances. |
| Approach: | They propose a model that utilizes lexical information in utterances to enhance backchannel (BC) prediction. |
| Outcome: | The proposed model showed 14.24% performance improvement compared to baseline in the four BC categories: continuer, understanding, empathic response, and No BC. |
Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to aid implicit discourse relation recognition (IDRR) lack explicit connectives and are difficult to implement on fine-grained IDRR. |
| Approach: | They propose a Prompt-based Connective Prediction method that instructs large-scale pre-trained models to use knowledge relevant to discourse relation and utilizes strong correlation between connectives and discourse relation to help the model recognize implicit discourse relations. |
| Outcome: | The proposed method surpasses the state-of-the-art model and achieves significant improvements on those fine-grained few-shot discourse relation classes. |
Revealing the Inherent Instructability of Pre-Trained Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained large language models perform multitask learning during their pre-training . a new technique, Response Tuning, removes the instruction and its corresponding mapping to the response from instruction tuning. |
| Approach: | They propose a method which removes the instruction and its mapping to the response from instruction tuning. |
| Outcome: | The proposed model can respond to a wide range of instructions . it can recognize and reject unsafe queries after learning from response data. |
Noise Correction on Subjective Datasets (2024.acl-long)
Copied to clipboard
| Challenge: | Annotator fatigue and changing opinions over time can distort dataset annotations. |
| Approach: | They propose to use multitask learning to learn a more accurate representation of diverse opinions by using loss-based label correction. |
| Outcome: | The proposed method can cleanly separate agreeing and disagreeing annotations and provides a controllable way to encourage or discourage disagreement. |
Localization of Fake News Detection via Multitask Transfer Learning (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for detecting fake news require large labeled datasets and expert-curated corpora, which low-resource languages may not have. |
| Approach: | They construct a benchmark dataset for fake news detection in Filipino using curated corpora and transfer learning techniques. |
| Outcome: | The proposed method can achieve 91% accuracy on a fake news dataset, reducing error by 14% compared to established baselines. |
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task (2021.acl-long)
Copied to clipboard
| 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. |
Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition (2022.lrec-1)
Copied to clipboard
| Challenge: | Anglicisms are a challenge in German speech recognition due to their irregular pronunciation compared to native German words. |
| Approach: | They propose a multitask sequence-to-sequence approach for grapheme-tophoneme conversion to improve the phonetization of Anglicisms. |
| Outcome: | The proposed model reduces the word error rate by 1 % and the Anglicism error rate, while still maintaining the accuracy of the baseline model. |
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding (2020.emnlp-main)
Copied to clipboard
| Challenge: | Room-Across-Room (RxR) is a vision-and-language navigation dataset that addresses gaps in existing ones by addressing known biases in paths and eliciting more references to visible entities. |
| Approach: | They introduce a new Vision-and-Language Navigation (VLN) dataset that addresses biases in paths and elicits more references to visible entities. |
| Outcome: | The proposed model learns from synchronized pose traces by focusing only on portions of the panorama attended to in human demonstrations. |
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding (2021.findings-acl)
Copied to clipboard
Hu Xu, Gargi Ghosh, Po-Yao Huang, Prahal Arora, Masoumeh Aminzadeh, Christoph Feichtenhofer, Florian Metze, Luke Zettlemoyer
| Challenge: | Existing methods for multimodal video understanding are task-specific, limiting their use for retrieval-style end tasks. |
| Approach: | They propose a task-agnostic multimodal pre-training approach that can accept video or text input, or both, for a variety of end tasks. |
| Outcome: | The proposed approach outperforms existing methods on a wider range of tasks while maintaining separability. |
Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures (2021.naacl-main)
Copied to clipboard
| Challenge: | Prior work on identifying narratives related to sexual abuse disclosures did not consider this as an independent task. |
| Approach: | They propose to identify narratives related to sexual abuse disclosures as a joint modeling task that leverages their emotional attributes through multitask learning. |
| Outcome: | The proposed model leverages emotional attributes of textual conversations to identify narratives related to sexual abuse disclosures in homogeneous and heterogeneously settings. |
Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to simultaneous speech-to-text translation suffer from error propagation and extra latency. |
| Approach: | They propose a new paradigm for simultaneous speech-to-text translation using two separate decoders . they use multitask learning to jointly learn these two tasks with a shared encoder . |
| Outcome: | The proposed method achieves substantially better translation quality at similar levels of latency. |
Find-2-Find: Multitask Learning for Anaphora Resolution and Object Localization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems require large number of accurate annotations, such as image-level labels and location-level labeling. |
| Approach: | They propose a joint anaphora resolution and object localization dataset targeting visual-linguistic ambiguity. |
| Outcome: | The proposed framework improves visual-linguistic alignment and object localization with one joint model compared to a strong single-task baseline. |
QASem Parsing: Text-to-text Modeling of QA-based Semantics (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work suggests the appeals of incorporating explicit semantic representations into NLP . semi-structured natural language structures provide an intermediate meaning-capturing representation . |
| Approach: | They propose a semi-structured natural-language representation of textual information . they examine input and output linearization strategies and multitask learning . |
| Outcome: | The proposed model is based on pre-trained sequence-to-sequence language models . it is easy to use and can be used for downstream tasks that benefit from it . |
Sequence Labeling Parsing by Learning across Representations (P19-1)
Copied to clipboard
| Challenge: | Constituency and dependency parsing are the main abstractions for representing syntactic structure of sentences . constituency parsers are considered disjointed tasks, and their improvements have been obtained separately. |
| Approach: | They propose to add auxiliary loss to constituency parsing paradigms and explore a model that parses both paradigms at no cost. |
| Outcome: | The proposed model outperforms single-task models by 1.05 F1 points and 0.62 UAS points for constituency parsing and dependency parsers. |
Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies show that multitask learning improves speech translation performance by utilizing word embedding as the intermediate. |
| Approach: | They propose to use word embedding as an intermediate to improve multitask ST models by utilizing word embeds as input. |
| Outcome: | The proposed model outperforms existing models with sufficient training data but is still lacking in the low-resource scenario. |
Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness (2024.findings-acl)
Copied to clipboard
| 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. |
Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge transfer models do not exploit compositionality of language, often relying on superficial features. |
| Approach: | They propose to use a knowledge distillation technique to fine tune RoBERTa, BERT and DistilBERT models to improve their performance. |
| Outcome: | The proposed models improve on the CoQA task with linguistic knowledge and are able to represent compositional and lexical information. |
A Sentiment and Emotion Aware Multimodal Multiparty Humor Recognition in Multilingual Conversational Setting (2022.coling-1)
Copied to clipboard
| Challenge: | Humor is an essential aspect of daily conversation, and people try to provoke humor in their talks. |
| Approach: | They propose a multitask framework that annotates Hindi utterances with sentiment and emotion classes. |
| Outcome: | The proposed framework improves on the recently released Hindi Humor dataset . it takes sentiment and emotion into account to understand humor . |
Continual Learning in Task-Oriented Dialogue Systems (2021.emnlp-main)
Copied to clipboard
Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Pascale Fung, Zhiguang Wang
| Challenge: | Existing continuous learning systems are not designed to add new domains and functionalities through time without incurring the high cost of retraining the whole system. |
| Approach: | They propose a first-ever continual learning benchmark for task-oriented dialogue systems . they propose 'architecture' method based on residual adapters to implement continual training . |
| Outcome: | The proposed architectural method performs better than multitask learning while being 20X faster in learning new domains. |
#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods based on latent topics cannot capture user interests and thus can't be used to predict how likely a user will post with a hashtag. |
| Approach: | They propose a personalized topic attention model that captures salient contents to personalize hashtag contexts by predicting how likely a user will post with a hashtag. |
| Outcome: | The proposed model significantly outperforms the state-of-the-art recommendation approach without exploiting latent topics. |
Symbolic Inductive Bias for Visually Grounded Learning of Spoken Language (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to processing spoken language are to first automatically transcribe it into text, but there is an alternative: end-to-end learning. |
| Approach: | They propose to use multitask learning to exploit existing transcribed speech within the end-to-end setting by matching spoken captions with corresponding images, speech with text, and text with images. |
| Outcome: | The proposed model improves image retrieval performance compared to training the speech/image task in isolation. |
AdapterShare: Task Correlation Modeling with Adapter Differentiation (2022.emnlp-main)
Copied to clipboard
| Challenge: | AdapterShare is an adapter differentiation method to explicitly model the task correlation among multiple tasks. |
| Approach: | They propose an adapter differentiation method to explicitly model the task correlation among multiple tasks. |
| Outcome: | The proposed method achieves 1.90 points improvement on five dialogue understanding tasks and 2.33 points gain on NLU tasks. |
Difficulty-Controllable Cloze Question Distractor Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating high-quality distractors lack adaptability and control over difficulty levels. |
| Approach: | They propose a two-way distractor generation process to generate plausible distractors using an ensemble QA system and a multitask learning strategy to train a difficulty-controllable generation model. |
| Outcome: | The proposed method significantly outperforms GPT-4o in aligning distractor difficulty with human perception. |
Exploring Distributional Shifts in Large Language Models for Code Analysis (2023.emnlp-main)
Copied to clipboard
| Challenge: | Since the late 2000s, researchers have been reporting poor generalization of statistical learning models to new software systems, such as GitHub Copilot, Amazon CodeWhisperer, Replit, etc. |
| Approach: | They systematically study how three large language models with code capabilities generalize to out-of-domain data. |
| Outcome: | The proposed model outperforms the existing model for code generation on multiple domains at once. |
Learning Semantic Role Labeling from Compatible Label Sequences (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has shown that cross-task interaction helps, but only explored multitask learning so far. |
| Approach: | They propose a framework that jointly models VerbNet and PropBank labels as one sequence and enforcing Semlink constraints during decoding improves the overall F1 . |
| Outcome: | The proposed model outperforms the prior best in-domain model by 3.5 (VerbNet) and 0.8 (PropBank). |
SPACE-IDEAS: A Dataset for Salient Information Detection in Space Innovation (2024.lrec-main)
Copied to clipboard
| Challenge: | Detecting salient parts in text is widely used to mitigate information overload. |
| Approach: | They propose a dataset for salient information detection from space innovation that is manually annotated using a large generative language model. |
| Outcome: | The proposed dataset can be leveraged using multitask learning to train better classifiers. |
DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents (2026.findings-acl)
Copied to clipboard
Kai Shi, Jun Yang, Ni Yang, Binqiang Pan, Qingsong Xie, null Zhangchao, Zhenyu Yang, Tianhuang Su, Haonan Lu
| Challenge: | Mobile Phone Agents (MPAs) have attracted huge attention due to their practicability in a multitude of scenarios. |
| Approach: | They propose a data mixture optimization solution that extrapolates optimal data mixtures from a trainable network. |
| Outcome: | The proposed model outperforms existing methods on open-source benchmarks and on open source benchmarks. |