TL
TL;DR
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, is presented.
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: this https URL
References20 items
1
Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
2
Multi-Task Learning for Machine Reading Comprehension
3
Read + Verify: Machine Reading Comprehension with Unanswerable Questions
4
Know What You Don’t Know: Unanswerable Questions for SQuAD
5