• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Acquiring domain knowledge during dialogues for dialogue systems

Research Project

Project/Area Number 16H02869
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionOsaka University

Principal Investigator

KOMATANI Kazunori  大阪大学, 産業科学研究所, 教授 (40362579)

Co-Investigator(Kenkyū-buntansha) 武田 龍  大阪大学, 産業科学研究所, 准教授 (20749527)
林 克彦  東京大学, 大学院情報理工学系研究科, 助教 (50725794)
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥16,250,000 (Direct Cost: ¥12,500,000、Indirect Cost: ¥3,750,000)
Fiscal Year 2018: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2017: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2016: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Keywords対話システム / ドメイン知識獲得 / 未知語 / 未知概念 / 暗黙的確認 / 質問選択 / 質問生成 / ドメイン知識 / 知識獲得
Outline of Final Research Achievements

We have studied towards an intelligent dialogue system that autonomously acquires domain knowledge and becomes smarter as we talk. Specifically, we proposed a process called implicit confirmation for acquiring knowledge about unknown terms that appear during dialogues, without reducing the user's willingness to talk. We also investigated and revealed the influence of the question types to acquire knowledge on the user's impression using crowdsourcing. Furthermore, we proposed a novel framework for selecting questions about knowledge unknown to the system, using a technique called knowledge graph completion.

Academic Significance and Societal Importance of the Research Achievements

対話システムが話しながら知識を獲得することは重要なトピックであり,ここ数年で海外のいくつかのグループでも研究が開始されている.その中でも我々のグループでは,ユーザの話す意欲を削がない手法に注力しており,このような観点からのアプローチは世界的にもまだ類を見ない.一見賢いがすぐに飽きられるような対話システムの次世代を考えるうえで,個人に応じてシステムが育つ技術は必須であり,それを実現するための基盤技術にあたる.

Report

(4 results)
  • 2019 Final Research Report ( PDF )
  • 2018 Annual Research Report
  • 2017 Annual Research Report
  • 2016 Annual Research Report
  • Research Products

    (25 results)

All 2019 2018 2017 2016 Other

All Journal Article (3 results) (of which Peer Reviewed: 2 results,  Open Access: 3 results) Presentation (21 results) (of which Int'l Joint Research: 8 results,  Invited: 2 results) Remarks (1 results)

  • [Journal Article] Proposal of Implicit Confirmation toward Lexical Acquisition during Dialogues2018

    • Author(s)
      大野 航平, 武田 龍, ニコルズ エリック, 中野 幹生, 駒谷 和範
    • Journal Title

      Transactions of the Japanese Society for Artificial Intelligence

      Volume: 33 Issue: 1 Pages: DSH-E_1-10

    • DOI

      10.1527/tjsai.DSH-E

    • NAID

      130006415587

    • ISSN
      1346-0714, 1346-8030
    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems2017

    • Author(s)
      Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano
    • Journal Title

      Dialogue and Discourse

      Volume: 8 Issue: 2 Pages: 206-224

    • DOI

      10.5087/dad.2017.209

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Speech Interaction based on Hierarchical Understanding of Spoken Utterances2016

    • Author(s)
      駒谷 和範
    • Journal Title

      Journal of The Society of Instrument and Control Engineers

      Volume: 55 Issue: 10 Pages: 878-883

    • DOI

      10.11499/sicejl.55.878

    • NAID

      130005431527

    • ISSN
      0453-4662, 1883-8170
    • Related Report
      2016 Annual Research Report
    • Open Access
  • [Presentation] Multimodal Dialogue Data Collection and Analysis of Annotation Disagreement2019

    • Author(s)
      Kazunori Komatani, Shogo Okada, Haruto Nishimoto, Masahiro Araki, Mikio Nakano
    • Organizer
      International Workshop on Spoken Dialogue Systems (IWSDS)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Word Segmentation from Phoneme Sequences based on Pitman-Yor Semi-Makov Model Exploiting Subword Information2018

    • Author(s)
      Ryu Takeda, Kazunori Komatani, Alexander Rudnicky
    • Organizer
      IEEE Workshop on Spoken Language Technology (SLT)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Investigating Effectiveness of Linguistic Features Based on Speech Recognition for Storytelling Skill Assessment2018

    • Author(s)
      Shogo Okada, Kazunori Komatani
    • Organizer
      The 31st International Conference on Industrial, Engineering and Other Applications of Applied Intelligence Systems (IEA/AIE-2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Collection of Multimodal Dialog Data and Analysis of the Result of Annotation of Users' Interests2018

    • Author(s)
      Masahiro Araki, Sayaka Tomimasu, Mikio Nakano, Kazunori Komatani, Shogo Okada, Shinya Fujie, Hiroaki Sugiyama
    • Organizer
      Language Resources and Evaluation Conference (LREC)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 配布可能なマルチモーダル対話データの収集とアノテーション不一致傾向の分析2018

    • Author(s)
      駒谷 和範, 岡田 将吾, 西本 遥人, 荒木 雅弘, 中野 幹生
    • Organizer
      第9回対話システムシンポジウム
    • Related Report
      2018 Annual Research Report
  • [Presentation] マルチモーダル対話における興味の有無の推定と追加コーパスを用いた性能評価2018

    • Author(s)
      西本 遥人, 武田 龍, 駒谷 和範
    • Organizer
      第9回対話システムシンポジウム
    • Related Report
      2018 Annual Research Report
  • [Presentation] 対話システムにおける知識グラフの埋め込み表現を用いた応答生成の試み2018

    • Author(s)
      藤岡 勇真, 林 克彦, 中野 幹生, 駒谷 和範
    • Organizer
      第9回対話システムシンポジウム
    • Related Report
      2018 Annual Research Report
  • [Presentation] 対話におけるマルチモーダル情報を用いたユーザの興味の有無の推定2018

    • Author(s)
      西本 遥人, 駒谷 和範
    • Organizer
      人工知能学会第32回全国大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 未知の属性の問合せに応答可能な対話システムを目指した知識グラフの拡充2018

    • Author(s)
      藤岡 勇真, 駒谷 和範
    • Organizer
      人工知能学会第32回全国大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 音声対話システムにおける対話の状況を利用した応答タイミング推定2018

    • Author(s)
      赤井 元紀, 武田 龍, 駒谷 和範
    • Organizer
      人工知能学会第32回全国大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 暗黙的確認による未知語獲得のためのユーザ応答に基づくクラス推定結果の正誤判別2018

    • Author(s)
      大野 航平, 武田 龍, ニコルズ エリック, 中野 幹生, 駒谷 和範
    • Organizer
      言語処理学会第24回年次大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Lexical Acquisition through Implicit Confirmations over Multiple Dialogues2017

    • Author(s)
      Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano and Kazunori Komatani
    • Organizer
      18th Annual SIGDIAL Meeting on Discourse and Dialogue
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context2017

    • Author(s)
      Ryu Takeda, Kazunori Komatani
    • Organizer
      International Joint Conference on Natural Language Processing (IJCNLP)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 対話中の未知語獲得のための正しいクラスに基づく暗黙的確認要求の抽出2017

    • Author(s)
      大野 航平, 武田 龍, 中野 幹生, ニコルズ エリック, 駒谷 和範
    • Organizer
      人工知能学会第31回全国大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 適応的な相槌生成のための複数の識別器の構築2017

    • Author(s)
      赤井 元紀, 武田 龍,駒谷 和範
    • Organizer
      情報科学技術フォーラム(FIT)
    • Related Report
      2017 Annual Research Report
  • [Presentation] Bayesian Language Model based on Mixture of Segmental Contexts for Spontaneous Utterances with Unexpected Words2016

    • Author(s)
      Ryu Takeda, Kazunori Komatani
    • Organizer
      International Conference on Computational Linguistics (COLING)
    • Place of Presentation
      Osaka, Japan
    • Year and Date
      2016-12-13
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 対話を通じた未知語のクラス獲得に向けた暗黙的確認の実現2016

    • Author(s)
      大野 航平, 武田 龍, Eric Nichols, 中野 幹生, 駒谷 和範
    • Organizer
      第78回言語・音声理解と対話処理研究会(SIG-SLUD)(第7回対話システムシンポジウム)
    • Place of Presentation
      早稲田大学
    • Year and Date
      2016-10-06
    • Related Report
      2016 Annual Research Report
  • [Presentation] Toward Lexical Acquisition during Dialogues through Implicit Confirmation for Closed-Domain Chatbots2016

    • Author(s)
      Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano, Kazunori Komatani
    • Organizer
      Second Workshop on Chatbots and Conversational Agent Technologies (WOCHAT)
    • Place of Presentation
      Los Angeles, CA, USA
    • Year and Date
      2016-09-20
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 音声対話システムにおける発話行動の階層的理解2016

    • Author(s)
      駒谷 和範
    • Organizer
      第111回音楽情報科学研究発表会(音学シンポジウム2016)
    • Place of Presentation
      東海大学高輪キャンパス
    • Year and Date
      2016-05-21
    • Related Report
      2016 Annual Research Report
    • Invited
  • [Presentation] 人とわかり合える音声対話ロボットの実現を目指して2016

    • Author(s)
      駒谷 和範
    • Organizer
      第226回自然言語処理研究会 第111回音声言語情報処理研究会 合同研究発表会
    • Place of Presentation
      東京工業大学
    • Year and Date
      2016-05-16
    • Related Report
      2016 Annual Research Report
    • Invited
  • [Presentation] 対話を通じた未知語獲得に向けた暗黙的確認の提案2016

    • Author(s)
      大野 航平, 武田 龍, エリック ニコルズ, 中野 幹生, 駒谷 和範
    • Organizer
      第226回自然言語処理研究会 第111回音声言語情報処理研究会 合同研究発表会
    • Place of Presentation
      東京工業大学
    • Year and Date
      2016-05-16
    • Related Report
      2016 Annual Research Report
  • [Remarks] AIが対話の流れから単語を学ぶ手法を開発

    • URL

      http://resou.osaka-u.ac.jp/ja/research/2017/20171221_1

    • Related Report
      2017 Annual Research Report

URL: 

Published: 2016-04-21   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi