Neural Discourse Structure for Text Categorization

Yangfeng Ji, Noah A. Smith


Abstract
We show that discourse structure, as defined by Rhetorical Structure Theory and provided by an existing discourse parser, benefits text categorization. Our approach uses a recursive neural network and a newly proposed attention mechanism to compute a representation of the text that focuses on salient content, from the perspective of both RST and the task. Experiments consider variants of the approach and illustrate its strengths and weaknesses.
Anthology ID:
P17-1092
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
996–1005
Language:
URL:
https://aclanthology.org/P17-1092
DOI:
10.18653/v1/P17-1092
Bibkey:
Cite (ACL):
Yangfeng Ji and Noah A. Smith. 2017. Neural Discourse Structure for Text Categorization. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 996–1005, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Neural Discourse Structure for Text Categorization (Ji & Smith, ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1092.pdf
Note:
 P17-1092.Notes.pdf
Video:
 https://aclanthology.org/P17-1092.mp4
Code
 jiyfeng/disco4textcat