Cross-language dialog state tracking using hierarchical attention mechanism계층적 어텐션 메커니즘을 이용한 교차 언어 대화 상태 추적

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 310
  • Download : 0
The dialog state tracking, which refers to identifying the user' s intent from the utterances, is one of the most important tasks in dialog management. In this paper, we present our dialog state tracker developed for the fifth dialog state tracking challenge (DSTC5), which focused on cross-language adaptation using machine-translated training data, which was very scarce compared to the size of the ontology. Our dialog state tracker is based on the bi-directional long short-term memory (LSTM) with a hierarchical attention mechanism in order to spot important words in user utterances. The intent prediction is done by finding the most relevant keyword in the ontology to the attention-weighted word vector. Our tracker thus has various advantages over existing approaches, such as predicting out-of-vocabulary (OOV) intent due to scarce training data or machine translation. We show that our tracker outperforms other trackers submitted to the challenge in terms of almost all performance measures.
Advisors
Kim, Kee-Eungresearcher김기응researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2018
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학부, 2018.2,[iv, 22 p. :]

Keywords

Dialog state tracking▼aAttention mechanism▼aHierarchical attention mechanism▼aCross-language; 대화 상태 추적▼a어텐션 메커니즘▼a계층적 어텐션 메커니즘▼a교차 언어

URI
http://hdl.handle.net/10203/267006
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=734083&flag=dissertation
Appears in Collection
CS-Theses_Master(석사논문)
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