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

This PyTorch package implements the Multi-Task Stochastic Answer Network (MT-SAN) for Machine Reading Comprehension, as described in:

Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu and Jianfeng Gao
Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension North American Chapter of the Association for Computational Linguistics (NAACL), 2019
arXiv version

Please cite the above paper if you use this code.

Results

We report single-model results produced by this package as follows.

Quickstart

Install via pip:

1. python3.6

2. install requirements > pip install -r requirements.txt

Use docker:

1. pull docker: We can use the same docker as mt-dnn > docker pull allenlao/pytorch-mt-dnn:v0.1

2. run docker > docker run -it --rm --runtime nvidia allenlao/pytorch-mt-dnn:v0.1 bash Please refer to the following link if you first use docker: https://docs.docker.com/

Train a MT-SAN Model

1. prepare data

   ./prepare_data.sh

2. train a model: See example codes in run.sh

Pretrained Models

You can download pretrained models with the best SQuAD performance here.

Notes and Acknowledgments

The code is developed based on the original SAN code: https://github.com/kevinduh/san_mrc

Related: MT-DNN

by [email protected]