Neural Discourse Structure for Text Categorization Article Swipe
Related Concepts
Computer science
Categorization
Natural language processing
Salient
Parsing
Artificial intelligence
Representation (politics)
Rhetorical question
Strengths and weaknesses
Perspective (graphical)
Task (project management)
Artificial neural network
Mechanism (biology)
Text categorization
Linguistics
Psychology
Law
Social psychology
Philosophy
Economics
Epistemology
Management
Politics
Political science
Yangfeng Ji
,
Noah A. Smith
·
YOU?
·
· 2017
· Open Access
·
· DOI: https://doi.org/10.18653/v1/p17-1092
· OA: W2586597293
YOU?
·
· 2017
· Open Access
·
· DOI: https://doi.org/10.18653/v1/p17-1092
· OA: W2586597293
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.
Related Topics
Finding more related topics…