Neural dialog state tracker for large ontologies by attention mechanism

Youngsoo Jang; Jiyeon Ham; Byung Jun Lee; Youngjae Chang; Kee Eung Kim

doi:10.1109/SLT.2016.7846314

Neural dialog state tracker for large ontologies by attention mechanism

Youngsoo Jang, Jiyeon Ham, Byung Jun Lee, Youngjae Chang, Kee Eung Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

13 Citations (Scopus)

Abstract

This paper presents a dialog state tracker submitted to Dialog State Tracking Challenge 5 (DSTC 5) with details. To tackle the challenging cross-language human-human dialog state tracking task with limited training data, we propose a tracker that focuses on words with meaningful context based on attention mechanism and bi-directional long short term memory (LSTM). The vocabulary including a plenty of proper nouns is vectorized with a sufficient amount of related texts crawled from web to learn a good embedding for words not existent in training dialogs. Despite its simplicity, our proposed tracker succeeded to achieve high accuracy without sophisticated pre- and post-processing.

Original language	English
Title of host publication	2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	531-537
Number of pages	7
ISBN (Electronic)	9781509049035
DOIs	https://doi.org/10.1109/SLT.2016.7846314
Publication status	Published - 2017 Feb 7
Externally published	Yes
Event	2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - San Diego, United States Duration: 2016 Dec 13 → 2016 Dec 16

Publication series

Name	2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings

Conference

Conference	2016 IEEE Workshop on Spoken Language Technology, SLT 2016
Country/Territory	United States
City	San Diego
Period	16/12/13 → 16/12/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Attention mechanism
Dialog state tracking
DSTC5
Recurrent Neural Network
Word embedding

ASJC Scopus subject areas

Human-Computer Interaction
Artificial Intelligence
Language and Linguistics
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/SLT.2016.7846314

Cite this

Jang, Y., Ham, J., Lee, B. J., Chang, Y., & Kim, K. E. (2017). Neural dialog state tracker for large ontologies by attention mechanism. In 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings (pp. 531-537). Article 7846314 (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SLT.2016.7846314

Neural dialog state tracker for large ontologies by attention mechanism. / Jang, Youngsoo; Ham, Jiyeon; Lee, Byung Jun et al.
2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 531-537 7846314 (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Jang, Y, Ham, J, Lee, BJ, Chang, Y & Kim, KE 2017, Neural dialog state tracker for large ontologies by attention mechanism. in 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings., 7846314, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 531-537, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016, San Diego, United States, 16/12/13. https://doi.org/10.1109/SLT.2016.7846314

Jang Y, Ham J, Lee BJ, Chang Y, Kim KE. Neural dialog state tracker for large ontologies by attention mechanism. In 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 531-537. 7846314. (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings). doi: 10.1109/SLT.2016.7846314

@inproceedings{06c8332fdff2482293b849e008742399,

title = "Neural dialog state tracker for large ontologies by attention mechanism",

abstract = "This paper presents a dialog state tracker submitted to Dialog State Tracking Challenge 5 (DSTC 5) with details. To tackle the challenging cross-language human-human dialog state tracking task with limited training data, we propose a tracker that focuses on words with meaningful context based on attention mechanism and bi-directional long short term memory (LSTM). The vocabulary including a plenty of proper nouns is vectorized with a sufficient amount of related texts crawled from web to learn a good embedding for words not existent in training dialogs. Despite its simplicity, our proposed tracker succeeded to achieve high accuracy without sophisticated pre- and post-processing.",

keywords = "Attention mechanism, Dialog state tracking, DSTC5, Recurrent Neural Network, Word embedding",

author = "Youngsoo Jang and Jiyeon Ham and Lee, {Byung Jun} and Youngjae Chang and Kim, {Kee Eung}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 ; Conference date: 13-12-2016 Through 16-12-2016",

year = "2017",

month = feb,

day = "7",

doi = "10.1109/SLT.2016.7846314",

language = "English",

series = "2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "531--537",

booktitle = "2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings",

}

TY - GEN

T1 - Neural dialog state tracker for large ontologies by attention mechanism

AU - Jang, Youngsoo

AU - Ham, Jiyeon

AU - Lee, Byung Jun

AU - Chang, Youngjae

AU - Kim, Kee Eung

PY - 2017/2/7

Y1 - 2017/2/7

N2 - This paper presents a dialog state tracker submitted to Dialog State Tracking Challenge 5 (DSTC 5) with details. To tackle the challenging cross-language human-human dialog state tracking task with limited training data, we propose a tracker that focuses on words with meaningful context based on attention mechanism and bi-directional long short term memory (LSTM). The vocabulary including a plenty of proper nouns is vectorized with a sufficient amount of related texts crawled from web to learn a good embedding for words not existent in training dialogs. Despite its simplicity, our proposed tracker succeeded to achieve high accuracy without sophisticated pre- and post-processing.

AB - This paper presents a dialog state tracker submitted to Dialog State Tracking Challenge 5 (DSTC 5) with details. To tackle the challenging cross-language human-human dialog state tracking task with limited training data, we propose a tracker that focuses on words with meaningful context based on attention mechanism and bi-directional long short term memory (LSTM). The vocabulary including a plenty of proper nouns is vectorized with a sufficient amount of related texts crawled from web to learn a good embedding for words not existent in training dialogs. Despite its simplicity, our proposed tracker succeeded to achieve high accuracy without sophisticated pre- and post-processing.

KW - Attention mechanism

KW - Dialog state tracking

KW - DSTC5

KW - Recurrent Neural Network

KW - Word embedding

UR - http://www.scopus.com/inward/record.url?scp=85016057191&partnerID=8YFLogxK

U2 - 10.1109/SLT.2016.7846314

DO - 10.1109/SLT.2016.7846314

M3 - Conference contribution

AN - SCOPUS:85016057191

T3 - 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings

SP - 531

EP - 537

BT - 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE Workshop on Spoken Language Technology, SLT 2016

Y2 - 13 December 2016 through 16 December 2016

ER -

Neural dialog state tracker for large ontologies by attention mechanism

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this