mlsanityData to 7 Oct 2026

Scheduled Multi-Task Learning: From Syntax to Translation

arXiv 1804.08915 ↗First posted 24 Apr 2018cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model begins learning syntax and translation interleaved, gradually putting more focus on translation. Using this approach, we achieve considerable improvements in terms of BLEU score on relatively large parallel corpus (WMT14 English to German) and a low-resource (WIT German to English) setup.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 3; 2024: 1; 2025: 0; 2026: 1.

18 papers.

Sort:

  1. 2021Syntax-BERT: Improving Pre-trained Transformers with Syntax Treescited by 51
  2. 2021Improving Multilingual Translation by Representation and Gradient Regularizationcited by 31
  3. 2021Specializing Multilingual Language Models: An Empirical Studycited by 21
  4. 2023Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflictscited by 21
  5. 2022Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusioncited by 18
  6. 2022Exploring the Role of Task Transferability in Large-Scale Multi-Task Learningcited by 17
  7. 2021Meta-Learning for Effective Multi-task and Multilingual Modellingcited by 13
  8. 2021Balancing Average and Worst-case Accuracy in Multitask Learningcited by 10
  9. 2021Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learningscited by 9
  10. 2024Comateformer: Combined Attention Transformer for Semantic Sentence Matchingcited by 9
  11. 2022Let the Model Decide its Curriculum for Multitask Learningcited by 8
  12. 2021Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsingcited by 7
6 more
  1. 2022Ultra Fast Speech Separation Model with Teacher Student Learningcited by 3
  2. 2023Hexatagging: Projective Dependency Parsing as Taggingcited by 3
  3. 2023Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspectivecited by 2
  4. 2021CUNI systems for WMT21: Multilingual Low-Resource Translation for Indo-European Languages Shared Taskcited by 1
  5. 2022On Parsing as Taggingcited by 0
  6. 2026Top-down string-to-dependency Neural Machine Translationcited by 0