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

by   Wei Peng, et al.

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.


page 1

page 2

page 3

page 4


Relation Module for Non-answerable Prediction on Question Answering

Machine reading comprehension(MRC) has attracted significant amounts of ...

QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization

Standard accuracy metrics indicate that modern reading comprehension sys...

Modeling Intention, Emotion and External World in Dialogue Systems

Intention, emotion and action are important elements in human activities...

Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering

This paper describes a novel hierarchical attention network for reading ...

DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification

In dialog system, dialog act recognition and sentiment classification ar...

Multi-Perspective Fusion Network for Commonsense Reading Comprehension

Commonsense Reading Comprehension (CRC) is a significantly challenging t...

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

Multi-hop textual question answering requires combining information from...

Please sign up or login with your details

Forgot password? Click here to reset