DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Kee eung | - |
dc.contributor.advisor | 김기응 | - |
dc.contributor.author | Ham, Jiyeon | - |
dc.date.accessioned | 2019-09-04T02:45:57Z | - |
dc.date.available | 2019-09-04T02:45:57Z | - |
dc.date.issued | 2018 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=828599&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/267007 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2018.8,[iii, 24 p. :] | - |
dc.description.abstract | Goal-oriented dialog systems require a different approach from chit-chat conversation systems in that they typically interact with an external knowledge base. It is desirable to incorporate domain knowledge to operate on the external knowledge. This paper presents extensions to hybrid code networks with reinforcement learning agent for the sixth dialog system technology (DSTC6) Facebook AI research (FAIR) dialog dataset. It reduced the effort in manually constructing the rules or additional labeling compared to the previous approaches. Thanks to the well-designed RL agents and reasonable domain-specific rules, the proposed model achieved high accuracy in the most of the test sets. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Goal-oriented dialog system▼areinforcement learning▼aneural networks | - |
dc.subject | 목적을 갖는 대화 시스템▼a강화 학습▼a뉴럴 네트워크 | - |
dc.title | Extensions to hybrid code networks with reinforcement learning | - |
dc.title.alternative | 강화학습을 통한 하이브리드 코드 네트워크의 확장 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 함지연 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.