Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions

Katsuya Yokoyama, Hiroaki Takatsu, Hiroshi Honda, Shinya Fujie, Tetsunori Kobayashi

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

Abstract

In human-human conversations, listeners often convey intentions to speakers through feedback consisting of reflexive short responses. The speakers recognize these intentions and change the conversational plans to make communication more efficient. These functions are expected to be effective in human-system conversations also; however, there is only a few systems using these functions or a research corpus including such functions. We created a corpus that consists of users' short responses to an actual conversation system and developed a model for recognizing the intention of these responses. First, we categorized the intention of feedback that affects the progress of conversations. We then collected 15604 short responses of users from 2060 conversation sessions using our news-delivery conversation system. Twelve annotators labeled each utterance based on intention through a listening test. We then designed our deep-neural-network-based intention recognition model using the collected data. We found that feedback in the form of questions, which is the most frequently occurring expression, was correctly recognized and contributed to the efficiency of the conversation system.

Original languageEnglish
Title of host publication2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages934-940
Number of pages7
ISBN (Electronic)9781538643341
DOIs
Publication statusPublished - 2019 Feb 11
Event2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Athens, Greece
Duration: 2018 Dec 182018 Dec 21

Publication series

Name2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings

Conference

Conference2018 IEEE Spoken Language Technology Workshop, SLT 2018
CountryGreece
CityAthens
Period18/12/1818/12/21

Fingerprint

conversation
Feedback
Communication
listener
neural network
news
efficiency
communication
Deep neural networks

Keywords

  • conversation
  • dialog system
  • intention

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Linguistics and Language

Cite this

Yokoyama, K., Takatsu, H., Honda, H., Fujie, S., & Kobayashi, T. (2019). Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions. In 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings (pp. 934-940). [8639523] (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SLT.2018.8639523

Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions. / Yokoyama, Katsuya; Takatsu, Hiroaki; Honda, Hiroshi; Fujie, Shinya; Kobayashi, Tetsunori.

2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 934-940 8639523 (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings).

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

Yokoyama, K, Takatsu, H, Honda, H, Fujie, S & Kobayashi, T 2019, Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions. in 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings., 8639523, 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 934-940, 2018 IEEE Spoken Language Technology Workshop, SLT 2018, Athens, Greece, 18/12/18. https://doi.org/10.1109/SLT.2018.8639523
Yokoyama K, Takatsu H, Honda H, Fujie S, Kobayashi T. Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions. In 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 934-940. 8639523. (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings). https://doi.org/10.1109/SLT.2018.8639523
Yokoyama, Katsuya ; Takatsu, Hiroaki ; Honda, Hiroshi ; Fujie, Shinya ; Kobayashi, Tetsunori. / Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions. 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 934-940 (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings).
@inproceedings{ef94c26c61bc4fac9b3f4a64bc5957ab,
title = "Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions",
abstract = "In human-human conversations, listeners often convey intentions to speakers through feedback consisting of reflexive short responses. The speakers recognize these intentions and change the conversational plans to make communication more efficient. These functions are expected to be effective in human-system conversations also; however, there is only a few systems using these functions or a research corpus including such functions. We created a corpus that consists of users' short responses to an actual conversation system and developed a model for recognizing the intention of these responses. First, we categorized the intention of feedback that affects the progress of conversations. We then collected 15604 short responses of users from 2060 conversation sessions using our news-delivery conversation system. Twelve annotators labeled each utterance based on intention through a listening test. We then designed our deep-neural-network-based intention recognition model using the collected data. We found that feedback in the form of questions, which is the most frequently occurring expression, was correctly recognized and contributed to the efficiency of the conversation system.",
keywords = "conversation, dialog system, intention",
author = "Katsuya Yokoyama and Hiroaki Takatsu and Hiroshi Honda and Shinya Fujie and Tetsunori Kobayashi",
year = "2019",
month = "2",
day = "11",
doi = "10.1109/SLT.2018.8639523",
language = "English",
series = "2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "934--940",
booktitle = "2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings",

}

TY - GEN

T1 - Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions

AU - Yokoyama, Katsuya

AU - Takatsu, Hiroaki

AU - Honda, Hiroshi

AU - Fujie, Shinya

AU - Kobayashi, Tetsunori

PY - 2019/2/11

Y1 - 2019/2/11

N2 - In human-human conversations, listeners often convey intentions to speakers through feedback consisting of reflexive short responses. The speakers recognize these intentions and change the conversational plans to make communication more efficient. These functions are expected to be effective in human-system conversations also; however, there is only a few systems using these functions or a research corpus including such functions. We created a corpus that consists of users' short responses to an actual conversation system and developed a model for recognizing the intention of these responses. First, we categorized the intention of feedback that affects the progress of conversations. We then collected 15604 short responses of users from 2060 conversation sessions using our news-delivery conversation system. Twelve annotators labeled each utterance based on intention through a listening test. We then designed our deep-neural-network-based intention recognition model using the collected data. We found that feedback in the form of questions, which is the most frequently occurring expression, was correctly recognized and contributed to the efficiency of the conversation system.

AB - In human-human conversations, listeners often convey intentions to speakers through feedback consisting of reflexive short responses. The speakers recognize these intentions and change the conversational plans to make communication more efficient. These functions are expected to be effective in human-system conversations also; however, there is only a few systems using these functions or a research corpus including such functions. We created a corpus that consists of users' short responses to an actual conversation system and developed a model for recognizing the intention of these responses. First, we categorized the intention of feedback that affects the progress of conversations. We then collected 15604 short responses of users from 2060 conversation sessions using our news-delivery conversation system. Twelve annotators labeled each utterance based on intention through a listening test. We then designed our deep-neural-network-based intention recognition model using the collected data. We found that feedback in the form of questions, which is the most frequently occurring expression, was correctly recognized and contributed to the efficiency of the conversation system.

KW - conversation

KW - dialog system

KW - intention

UR - http://www.scopus.com/inward/record.url?scp=85063081871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063081871&partnerID=8YFLogxK

U2 - 10.1109/SLT.2018.8639523

DO - 10.1109/SLT.2018.8639523

M3 - Conference contribution

T3 - 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings

SP - 934

EP - 940

BT - 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -