A Co-Matching Model for Multi-choice Reading Comprehension

06/11/2018
by   Shuohang Wang, et al.
0

Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair. This paper proposes a new co-matching approach to this problem, which jointly models whether a passage can match both a question and a candidate answer. Experimental results on the RACE dataset demonstrate that our approach achieves state-of-the-art performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2019

Dual Co-Matching Network for Multi-choice Reading Comprehension

Multi-choice reading comprehension is a challenging task that requires c...
research
05/06/2018

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification

Machine reading comprehension (MRC) on real web data usually requires th...
research
05/16/2018

Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension

While sophisticated neural-based techniques have been developed in readi...
research
11/02/2017

Multi-Mention Learning for Reading Comprehension with Neural Cascades

Reading comprehension is a challenging task, especially when executed ac...
research
02/26/2020

Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension

Multiple-choice Machine Reading Comprehension (MRC) is an important and ...
research
01/08/2019

Multi-Perspective Fusion Network for Commonsense Reading Comprehension

Commonsense Reading Comprehension (CRC) is a significantly challenging t...
research
09/10/2018

Exploring Machine Reading Comprehension with Explicit Knowledge

To apply general knowledge to machine reading comprehension (MRC), we pr...

Please sign up or login with your details

Forgot password? Click here to reset