mlsanityData to 14 Oct 2026

When is multitask learning effective? Semantic sequence prediction under varying data conditions

arXiv 1612.02251 ↗First posted 7 Dec 2016cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine its success. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary tasks, amongst which a novel setup, and correlate their impact to data-dependent conditions. Our results show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 5; 2023: 4; 2024: 2; 2025: 1.

21 papers.

Sort:

  1. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 110
  2. 2021Multi-Task Learning in Natural Language Processing: An Overviewcited by 62
  3. 2021PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrievalcited by 50
  4. 2023π-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolationcited by 40
  5. 2022GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learningcited by 36
  6. 2021De-identification of Privacy-related Entities in Job Postingscited by 12
  7. 2023Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learningcited by 9
  8. 2022Multi-Task Meta Learning: learn how to adapt to unseen taskscited by 8
  9. 2021Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translationcited by 6
  10. 2021Latent-Optimized Adversarial Neural Transfer for Sarcasm Detectioncited by 6
  11. 2021A Flexible Multi-Task Model for BERT Servingcited by 4
  12. 2022Generative multitask learning mitigates target-causing confoundingcited by 4
9 more
  1. 2024Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Informationcited by 4
  2. 2021One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasetscited by 3
  3. 2021SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learningcited by 3
  4. 2022Polarity and Subjectivity Detection with Multitask Learning and BERT Embeddingcited by 3
  5. 2023CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet Extractioncited by 3
  6. 2025Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Studycited by 3
  7. 2022On Steering Multi-Annotations per Sample for Multi-Task Learningcited by 0
  8. 2023Label Agnostic Pre-training for Zero-shot Text Classificationcited by 0
  9. 2024On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalizationcited by 0