MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension

TL;DR

This paper introduces MCR-Net, a novel multi-step co-interactive relation network that explicitly models question-passage interactions to improve unanswerable question detection in machine reading comprehension, outperforming existing baselines.

Contribution

The paper presents a new multi-step co-interactive relation network that explicitly captures mutual question-passage relations for better unanswerable question detection.

Findings

Achieves state-of-the-art results on SQuAD 2.0 and DuReader datasets.

Outperforms BERT-style baselines in unanswerable question detection.

Visualization confirms the importance of mutual interaction modeling.

Abstract

Question answering systems usually use keyword searches to retrieve potential passages related to a question, and then extract the answer from passages with the machine reading comprehension methods. However, many questions tend to be unanswerable in the real world. In this case, it is significant and challenging how the model determines when no answer is supported by the passage and abstains from answering. Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions. To tackle this problem, we propose a Multi-Step Co-Interactive Relation Network (MCR-Net) to explicitly model the mutual interaction and locate key clues from coarse to fine by introducing a co-interactive relation module. The co-interactive relation module contains a stack of interaction and fusion blocks to continuously integrate and fuse history-guided and current-query-guided clues in an explicit way. Experiments on the SQuAD 2.0 and DuReader datasets show that our model achieves a remarkable improvement, outperforming the BERT-style baselines in literature. Visualization analysis also verifies the importance of the mutual interaction between the question and passage.