Read + Verify: Machine Reading Comprehension with Unanswerable Questions

TL;DR

This paper introduces a read-then-verify system for machine reading comprehension with unanswerable questions, improving answer validation by verifying the legitimacy of predicted answers, leading to state-of-the-art results on SQuAD 2.0.

Contribution

It proposes a novel read-then-verify framework with auxiliary losses and multiple verifier architectures to enhance answer validation in unanswerable question scenarios.

Findings

Achieves 74.2 F1 score on SQuAD 2.0 test set.

Outperforms previous models in unanswerable question detection.

Demonstrates effectiveness of answer verification in MRC systems.

Abstract

Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred. In addition to extract answers, previous works usually predict an additional "no-answer" probability to detect unanswerable cases. However, they fail to validate the answerability of the question by verifying the legitimacy of the predicted answer. To address this problem, we propose a novel read-then-verify system, which not only utilizes a neural reader to extract candidate answers and produce no-answer probabilities, but also leverages an answer verifier to decide whether the predicted answer is entailed by the input snippets. Moreover, we introduce two auxiliary losses to help the reader better handle answer extraction as well as no-answer detection, and investigate three different architectures for the answer verifier. Our experiments on the SQuAD 2.0 dataset show that our system achieves a score of 74.2 F1 on the test set, achieving state-of-the-art results at the time of submission (Aug. 28th, 2018).