Skip to main navigation Skip to search Skip to main content

Robust Machine Reading Comprehension by Learning Soft labels

  • Harbin Institute of Technology
  • Tencent
  • Japan National Institute of Information and Communications Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Neural models have achieved great success on the task of machine reading comprehension (MRC), which are typically trained on hard labels. We argue that hard labels limit the model capability on generalization due to the label sparseness problem. In this paper, we propose a robust training method for MRC models to address this problem. Our method consists of three strategies, 1) label smoothing, 2) word overlapping, 3) distribution prediction. All of them help to train models on soft labels. We validate our approach on the representative architecture - ALBERT. Experimental results show that our method can greatly boost the baseline with 1% improvement in average, and achieve state-of-the-art performance on NewsQA and QUOREF.

Original languageEnglish
Title of host publicationCOLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference
EditorsDonia Scott, Nuria Bel, Chengqing Zong
PublisherAssociation for Computational Linguistics (ACL)
Pages2754-2759
Number of pages6
ISBN (Electronic)9781952148279
StatePublished - 2020
Event28th International Conference on Computational Linguistics, COLING 2020 - Virtual, Online, Spain
Duration: 8 Dec 202013 Dec 2020

Publication series

NameCOLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

Conference

Conference28th International Conference on Computational Linguistics, COLING 2020
Country/TerritorySpain
CityVirtual, Online
Period8/12/2013/12/20

Fingerprint

Dive into the research topics of 'Robust Machine Reading Comprehension by Learning Soft labels'. Together they form a unique fingerprint.

Cite this