Dialog state tracking with attention-based sequence-to-sequence learning

Takaaki Hori, Hai Wang, Chiori Hori, Shinji Watanabe, Bret Harsham, Jonathan Le Roux, John R. Hershey, Yusuke Koji, Yi Jing, Zhaocheng Zhu, Takeyuki Aikawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

We present an advanced dialog state tracking system designed for the 5th Dialog State Tracking Challenge (DSTC5). The main task of DSTC5 is to track the dialog state in a human-human dialog. For each utterance, the tracker emits a frame of slot-value pairs considering the full history of the dialog up to the current turn. Our system includes an encoder-decoder architecture with an attention mechanism to map an input word sequence to a set of semantic labels, i.e., slot-value pairs. This handles the problem of the unknown alignment between the utterances and the labels. By combining the attention-based tracker with rule-based trackers elaborated for English and Chinese, the F-score for the development set improved from 0.475 to 0.507 compared to the rule-only trackers. Moreover, we achieved 0.517 F-score by refining the combination strategy based on the topic and slot level performance of each tracker. In this paper, we also validate the efficacy of each technique and report the test set results submitted to the challenge.

Original languageEnglish
Title of host publication2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages552-558
Number of pages7
ISBN (Electronic)9781509049035
DOIs
Publication statusPublished - 2017 Feb 7
Externally publishedYes
Event2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - San Diego, United States
Duration: 2016 Dec 132016 Dec 16

Other

Other2016 IEEE Workshop on Spoken Language Technology, SLT 2016
CountryUnited States
CitySan Diego
Period16/12/1316/12/16

Fingerprint

Labels
Refining
Semantics
Sequence Learning
Utterance

Keywords

  • Attention model
  • Dialog state tracking
  • Encoder-decoder
  • Long short-term memory
  • Sequence-to-sequence learning

ASJC Scopus subject areas

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

Cite this

Hori, T., Wang, H., Hori, C., Watanabe, S., Harsham, B., Le Roux, J., ... Aikawa, T. (2017). Dialog state tracking with attention-based sequence-to-sequence learning. In 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings (pp. 552-558). [7846317] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SLT.2016.7846317

Dialog state tracking with attention-based sequence-to-sequence learning. / Hori, Takaaki; Wang, Hai; Hori, Chiori; Watanabe, Shinji; Harsham, Bret; Le Roux, Jonathan; Hershey, John R.; Koji, Yusuke; Jing, Yi; Zhu, Zhaocheng; Aikawa, Takeyuki.

2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 552-558 7846317.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hori, T, Wang, H, Hori, C, Watanabe, S, Harsham, B, Le Roux, J, Hershey, JR, Koji, Y, Jing, Y, Zhu, Z & Aikawa, T 2017, Dialog state tracking with attention-based sequence-to-sequence learning. in 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings., 7846317, Institute of Electrical and Electronics Engineers Inc., pp. 552-558, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016, San Diego, United States, 16/12/13. https://doi.org/10.1109/SLT.2016.7846317
Hori T, Wang H, Hori C, Watanabe S, Harsham B, Le Roux J et al. Dialog state tracking with attention-based sequence-to-sequence learning. In 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 552-558. 7846317 https://doi.org/10.1109/SLT.2016.7846317
Hori, Takaaki ; Wang, Hai ; Hori, Chiori ; Watanabe, Shinji ; Harsham, Bret ; Le Roux, Jonathan ; Hershey, John R. ; Koji, Yusuke ; Jing, Yi ; Zhu, Zhaocheng ; Aikawa, Takeyuki. / Dialog state tracking with attention-based sequence-to-sequence learning. 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 552-558
@inproceedings{28d58adf952c4c6d8b0146991a9b23d9,
title = "Dialog state tracking with attention-based sequence-to-sequence learning",
abstract = "We present an advanced dialog state tracking system designed for the 5th Dialog State Tracking Challenge (DSTC5). The main task of DSTC5 is to track the dialog state in a human-human dialog. For each utterance, the tracker emits a frame of slot-value pairs considering the full history of the dialog up to the current turn. Our system includes an encoder-decoder architecture with an attention mechanism to map an input word sequence to a set of semantic labels, i.e., slot-value pairs. This handles the problem of the unknown alignment between the utterances and the labels. By combining the attention-based tracker with rule-based trackers elaborated for English and Chinese, the F-score for the development set improved from 0.475 to 0.507 compared to the rule-only trackers. Moreover, we achieved 0.517 F-score by refining the combination strategy based on the topic and slot level performance of each tracker. In this paper, we also validate the efficacy of each technique and report the test set results submitted to the challenge.",
keywords = "Attention model, Dialog state tracking, Encoder-decoder, Long short-term memory, Sequence-to-sequence learning",
author = "Takaaki Hori and Hai Wang and Chiori Hori and Shinji Watanabe and Bret Harsham and {Le Roux}, Jonathan and Hershey, {John R.} and Yusuke Koji and Yi Jing and Zhaocheng Zhu and Takeyuki Aikawa",
year = "2017",
month = "2",
day = "7",
doi = "10.1109/SLT.2016.7846317",
language = "English",
pages = "552--558",
booktitle = "2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Dialog state tracking with attention-based sequence-to-sequence learning

AU - Hori, Takaaki

AU - Wang, Hai

AU - Hori, Chiori

AU - Watanabe, Shinji

AU - Harsham, Bret

AU - Le Roux, Jonathan

AU - Hershey, John R.

AU - Koji, Yusuke

AU - Jing, Yi

AU - Zhu, Zhaocheng

AU - Aikawa, Takeyuki

PY - 2017/2/7

Y1 - 2017/2/7

N2 - We present an advanced dialog state tracking system designed for the 5th Dialog State Tracking Challenge (DSTC5). The main task of DSTC5 is to track the dialog state in a human-human dialog. For each utterance, the tracker emits a frame of slot-value pairs considering the full history of the dialog up to the current turn. Our system includes an encoder-decoder architecture with an attention mechanism to map an input word sequence to a set of semantic labels, i.e., slot-value pairs. This handles the problem of the unknown alignment between the utterances and the labels. By combining the attention-based tracker with rule-based trackers elaborated for English and Chinese, the F-score for the development set improved from 0.475 to 0.507 compared to the rule-only trackers. Moreover, we achieved 0.517 F-score by refining the combination strategy based on the topic and slot level performance of each tracker. In this paper, we also validate the efficacy of each technique and report the test set results submitted to the challenge.

AB - We present an advanced dialog state tracking system designed for the 5th Dialog State Tracking Challenge (DSTC5). The main task of DSTC5 is to track the dialog state in a human-human dialog. For each utterance, the tracker emits a frame of slot-value pairs considering the full history of the dialog up to the current turn. Our system includes an encoder-decoder architecture with an attention mechanism to map an input word sequence to a set of semantic labels, i.e., slot-value pairs. This handles the problem of the unknown alignment between the utterances and the labels. By combining the attention-based tracker with rule-based trackers elaborated for English and Chinese, the F-score for the development set improved from 0.475 to 0.507 compared to the rule-only trackers. Moreover, we achieved 0.517 F-score by refining the combination strategy based on the topic and slot level performance of each tracker. In this paper, we also validate the efficacy of each technique and report the test set results submitted to the challenge.

KW - Attention model

KW - Dialog state tracking

KW - Encoder-decoder

KW - Long short-term memory

KW - Sequence-to-sequence learning

UR - http://www.scopus.com/inward/record.url?scp=85015997608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015997608&partnerID=8YFLogxK

U2 - 10.1109/SLT.2016.7846317

DO - 10.1109/SLT.2016.7846317

M3 - Conference contribution

AN - SCOPUS:85015997608

SP - 552

EP - 558

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -