DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Myaeng, Sung Hyon | - |
dc.contributor.advisor | 맹성현 | - |
dc.contributor.author | Lee, Kangwook | - |
dc.date.accessioned | 2019-08-25T02:47:43Z | - |
dc.date.available | 2019-08-25T02:47:43Z | - |
dc.date.issued | 2018 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=734423&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/265326 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전산학부, 2018.2,[vi, 79 p. :] | - |
dc.description.abstract | 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. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Text Model▼aText Classification▼aDeep Neural Network▼aDiscourse Analysis | - |
dc.subject | Distributed Representation | - |
dc.subject | 텍스트 모델▼a텍스트 분류▼a심층 신경망▼a담화 분석▼a분산 표상 | - |
dc.title | Deep neural networks incorporating discourse information for modeling text | - |
dc.title.alternative | 텍스트 모델링을 위한 담화 정보 기반의 심층 인공 신경망 연구 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 이강욱 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.