Deep neural networks incorporating discourse information for modeling text = 텍스트 모델링을 위한 담화 정보 기반의 심층 인공 신경망 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 219
  • Download : 0
Capturing semantics scattered across entire text is one of the important issues for NLP tasks. It would be particularly critical with long text embodying a flow of themes. This paper proposes a new text modeling method that can handle thematic flows of text with Deep Neural Networks (DNN) in such a way that discourse information and distributed representations of text are incorporate. Unlike previous DNN-based document models, the proposed model enables discourse-aware analysis of text and composition of sentence-level distributed representations guided by the discourse structure. More specifically, my method identifies Elementary Discourse Units (EDUs) and their discourse relations in a given document by applying Rhetorical Structure Theory (RST)-based discourse analysis. The result is fed into a tree-structured neural network that reflects the discourse information including the structure of the document and the discourse roles and relation types. I evaluate the document model for two document-level text classification tasks, sentiment analysis and sarcasm detection, with comparisons against the reference systems that also utilize discourse information. In addition, I conduct additional experiments to evaluate the impact of neural network types and adopted discourse factors on modeling documents vis-à-vis the two classification tasks. Furthermore, I investigate the effects of various learning methods, input units on the quality of the proposed discourse-aware document model.
Advisors
Myaeng, Sung Hyonresearcher맹성현researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2018
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전산학부, 2018.2,[vi, 79 p. :]

Keywords

Text Model▼aText Classification▼aDeep Neural Network▼aDiscourse Analysis; Distributed Representation; 텍스트 모델▼a텍스트 분류▼a심층 신경망▼a담화 분석▼a분산 표상

URI
http://hdl.handle.net/10203/265326
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=734423&flag=dissertation
Appears in Collection
CS-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0