Enhancing Machine Reading Comprehension With Position Information

When people do the reading comprehension, they often try to find the words from the passages which are similar to the question words first. Then people deduce the answer based on the context around these similar words. Therefore, the position information may be helpful in finding the answer rapidly...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.141602-141611
Main Authors: Xu, Yajing, Liu, Weijie, Chen, Guang, Ren, Boya, Zhang, Siman, Gao, Sheng, Guo, Jun
Format: Article
Language:English
Subjects:
Attention mechanism
Coders
Computational modeling
Context
Context modeling
Kernel
Knowledge discovery
machine comprehension
Natural languages
North American Industry Classification System
position information
Predictive models
Questions
Reading comprehension
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:When people do the reading comprehension, they often try to find the words from the passages which are similar to the question words first. Then people deduce the answer based on the context around these similar words. Therefore, the position information may be helpful in finding the answer rapidly and is useful for reading comprehension. However, previous attention-based machine reading comprehension models typically focus on the interaction between the question and the context representation without considering the position information. In this paper, we introduce the position information to machine reading comprehension and investigate the performance of the position information. The position information is experimented in three different ways: 1) position encoder; 2) attention mechanism; and 3) position mapping embedding. By experimenting on TriviaQA dataset, we have demonstrated the effectiveness of position information.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2930407