This paper presents an extension of the Stochastic Answer Network (SAN), one of the state-of-the-art machine reading comprehension models, to be able to judge whether a question is unanswerable or not. The extended SAN contains two components: a span detector and a binary classifier for judging whether the question is unanswerable, and both components are jointly optimized. Experiments show that SAN achieves the results competitive to the state-of-the-art on Stanford Question Answering Dataset (SQuAD) 2.0. To facilitate the research on this field, we release our code: https://github.com/kevinduh/san_mrc.
Cite
@article{arxiv.1809.09194,
title = {Stochastic Answer Networks for SQuAD 2.0},
author = {Xiaodong Liu and Wei Li and Yuwei Fang and Aerin Kim and Kevin Duh and Jianfeng Gao},
journal= {arXiv preprint arXiv:1809.09194},
year = {2018}
}