Stochastic Answer Networks for Machine Reading Comprehension

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

Xiaodong Liu, Yelong Shen, Kevin Duh, Jianfeng Gao
Stochastic Answer Networks for Machine Reading Comprehension
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
arXiv version

Xiaodong Liu, Wei Li, Yuwei Fang, Aerin Kim, Kevin Duh and Jianfeng Gao
Stochastic Answer Networks for SQuAD 2.0
Technical Report arXiv version

Please cite the above papers if you use this code.

Quickstart

Setup Environment

1. python3.6
2. install requirements:

   pip install -r requirements.txt

3. download data/word2vec

   sh download.sh

4. You might need to download the en module for spacy

   python -m spacy download en # default English model (~50MB)
   python -m spacy download en_core_web_md # larger English model (~1GB)

Or pull our published docker: allenlao/pytorch-allennlp-rt

Train a SAN Model on SQuAD v1.1

1. preprocess data

   python prepro.py

2. train a model

   python train.py

Train a SAN Model on SQuAD v2.0

1. preprocess data

   python prepro.py --v2_on

2. train a Model

   python train.py --v2_on --dev_gold data\dev-v2.0.json

Use of ELMo

1. download ELMo resource from AllenNLP
2. train a Model with ELMo

   python train.py --elmo_on

Note that we only tested on SQuAD v1.1.

TODO

1. Multi-Task Training.
2. Add BERT.

Notes and Acknowledgments

Some of code are adapted from: https://github.com/hitvoice/DrQA
ELMo is from: https://allennlp.org

Results

We report results produced by this package as follows.

Related:

1. Multi-Task Learning for MRC
2. NLI