English

Stochastic Answer Networks for SQuAD 2.0

Computation and Language 2018-09-26 v1

Abstract

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}
}

Comments

6 pages, 2 figures and 2 tables

R2 v1 2026-06-23T04:17:03.946Z