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

September 18, 2018 · Entered Twilight · 🏛 North American Chapter of the Association for Computational Linguistics

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE.txt, README.md, config.py, dataset_configs, elmo_configs, my_utils, prepare_data.sh, prepro.py, requirements.txt, run.sh, src, train.py

Authors Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, Jianfeng Gao arXiv ID 1809.06963 Category cs.CL: Computation & Language Cross-listed cs.LG Citations 51 Venue North American Chapter of the Association for Computational Linguistics Repository https://github.com/xycforgithub/MultiTask-MRC ⭐ 102 Last Checked 1 month ago

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.