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

03/08/2021
by   Wei Peng, et al.
9

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/23/2019

Relation Module for Non-answerable Prediction on Question Answering

Machine reading comprehension(MRC) has attracted significant amounts of ...
08/31/2019

QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization

Standard accuracy metrics indicate that modern reading comprehension sys...
02/14/2022

Modeling Intention, Emotion and External World in Dialogue Systems

Intention, emotion and action are important elements in human activities...
08/16/2020

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...
11/16/2017

An Abstractive approach to Question Answering

Question Answering has come a long way from answer sentence selection, r...
01/08/2019

Multi-Perspective Fusion Network for Commonsense Reading Comprehension

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