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

Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, Jianfeng Gao
9/18/2018
cs.CLcs.LG

Official code: xycforgithub/MultiTask-MRC (102 stars, BSD-3-Clause, last commit 2020-09-07).

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.

View on arXivView PDF

Code Implementations(1)

xycforgithub/MultiTask-MRCOfficial100%
BSD-3-Clause

Multitask Learning for Machine Reading Comprehension, NAACL 2019

10221Shell, PythonMar 17, 20196 years agoBSD-3-Clause

Similar Papers

Order Matters in the Presence of Dataset Imbalance for Multilingual Learning

85% match2023

FonMTL: Towards Multitask Learning for the Fon Language

84% match1 repo52023

BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning

84% match1 repo862019

A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks

84% match1 repo232016

Knowledge Distillation for Multi-task Learning

84% match1 repo782020

AdaMerging: Adaptive Model Merging for Multi-Task Learning

84% match1 repo1162023

Cite this paper

@article{xu2018multitask,
  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},
  year   = {2018},
  eprint = {1809.06963},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1809.06963}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1809.06963.svg)](https://codeofpaper.com/paper/1809.06963)

Discussion