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.
- python3.6
- install requirements:
pip install -r requirements.txt
- prepare data
./prepare_data.sh
- train a model: See example codes in run.sh
The code is developed based on the original SAN code: https://github.com/kevinduh/san_mrc