Neural Discourse Structure for Text Categorization
نویسندگان
چکیده
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.
منابع مشابه
The categorization of “Iran’s handicrafts” at the intersection of “Westernism discourse” with “Orientalism discourse” in the Qajar period
This article intends to research the categorization and separation of “handicraft of Iran” in relation to the “Westernism” and “Orientalism” discourses in the Qajar discursive atmosphere by discourse analysis method and answers the questions of how “Handicrafts” is categorized at this intersection in the Qajar period, and how did these applied works changed into functional objects in the servic...
متن کاملUsing Discourse Analysis to Improve Text Categorization in MEDLINE
PROBLEM Automatic keyword assignment has been largely studied in medical informatics in the context of the MEDLINE database, both for helping search in MEDLINE and in order to provide an indicative "gist" of the content of an article. Automatic assignment of Medical Subject Headings (MeSH), which is formally an automatic text categorization task, has been proposed using different methods or com...
متن کاملThe Prosody of Discourse Structure and Content in the Production of Persian EFL Learners
The present research addressed the prosodic realization of global and local text structure and content in the spoken discourse data produced by Persian EFL learners. Two newspaper articles were analyzed using Rhetorical Structure Theory. Based on these analyses, the global structure in terms of hierarchical level, the local structure in terms of the relative importance of text segments and the ...
متن کاملTag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification
Identifying implicit discourse relations between text spans is a challenging task because it requires understanding the meaning of the text. To tackle this task, recent studies have tried several deep learning methods but few of them exploited the syntactic information. In this work, we explore the idea of incorporating syntactic parse tree into neural networks. Specifically, we employ the Tree...
متن کاملEffective Use of Word Order for Text Categorization with Convolutional Neural Networks
Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data. This paper studies CNN on text categorization to exploit the 1D structure (namely, word order) of text data for accurate prediction. Instead of using low-dimensional word vectors as input as is often done, we directly apply CNN to high-dimensional te...
متن کامل