English

Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension

Computation and Language 2019-04-02 v3 Machine Learning

Abstract

We propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains. Inspired by recent ideas of data selection in machine translation, we develop a novel sample re-weighting scheme to assign sample-specific weights to the loss. Empirical study shows that our approach can be applied to many existing MRC models. Combined with contextual representations from pre-trained language models (such as ELMo), we achieve new state-of-the-art results on a set of MRC benchmark datasets. We release our code at https://github.com/xycforgithub/MultiTask-MRC.

Keywords

Cite

@article{arxiv.1809.06963,
  title  = {Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension},
  author = {Yichong Xu and Xiaodong Liu and Yelong Shen and Jingjing Liu and Jianfeng Gao},
  journal= {arXiv preprint arXiv:1809.06963},
  year   = {2019}
}

Comments

North American Chapter of the Association for Computational Linguistics (NAACL) 2019

R2 v1 2026-06-23T04:10:54.056Z