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

Automatic evaluation of group discussion based on multi-modal interpretation

Research Project

Project/Area Number 20K12110
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 62030:Learning support system-related
Research InstitutionKyushu Institute of Technology

Principal Investigator

Shimada Kazutaka  九州工業大学, 大学院情報工学研究院, 教授 (50346863)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywordsマルチモーダル / 自然言語処理 / 議論分析 / グループディスカッション
Outline of Research at the Start

複数人による議論は,PBLのような学習の場のみならず,入試などのグループディスカッションでも活用され,教育の中で重要な役割を担っている.一方で,そのような議論を試験として公平にかつ効率的に評価することは難しい.本研究では,議論の流れを言語的な発話内容だけではなく,音声(韻律情報など)や画像(表情やしぐさなど)を踏まえ,マルチモーダルに利用して把握する手法の確立を目指す.得られた議論状態に基づき複数の評価の観点(軸)を対象とした議論評価システムの構築を進める.また,単に評価軸の可視化のみならず,それを言語的に説明する評価レポートの自動作成も試みる.

Outline of Final Research Achievements

In education, active learning, such as PBL, in which multiple people discuss issues for which there are no clear answers, has gained importance in recent years. We have studied the methods for understanding multi-party discussions and the summarisation techniques. On the other hand, evaluating debate discussions is necessary in education. However, it is not easy for evaluators to assess the quality and content of debates. In this research project, we created a dataset for evaluating the quality of debate and proposed a multimodal estimation model for estimating it. We also proposed and evaluated methods for various elemental techniques related to discussion analysis, not only on the created data but also on existing datasets (AMI corpus and our corpus created in the past).
In this research project, we created three datasets, and the datasets are available on the web.

Academic Significance and Societal Importance of the Research Achievements

本申請課題で作成したデータは基本的にすべて無償で申請者のWebページに公開している.これらのデータは関連研究者が自由に利用することができ,学術的な意義がある.
本申請課題で対象としている議論の評価は人間でさえも評価がぶれ,公平性などの様々な問題が生じる.この問題に対して,機械による客観的な評価が可能であれば,一定の意義がある.これは,デイベートや小論文などの自動評価という観点で社会的な意義がある.

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (28 results)

All 2024 2023 2022 2021 2020 Other

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (24 results) (of which Int'l Joint Research: 13 results) Remarks (3 results)

  • [Journal Article] Recognizing a participant behavior in a multi-party conversation2022

    • Author(s)
      Shunsuke Yonemitsu and Kazutaka Shimada
    • Journal Title

      Information Engineering Express

      Volume: 8 Issue: 1 Pages: 1

    • DOI

      10.52731/iee.v8.i1.635

    • ISSN
      2185-9884, 2185-9892
    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] 能動学習と局所対話への特化を考慮した対話文における言い淀み検出2024

    • Author(s)
      中島 寛人, 嶋田 和孝
    • Organizer
      火の国シンポジウム2024, B-4-3, 2024.
    • Related Report
      2023 Annual Research Report
  • [Presentation] Automated Scoring of Logical Consistency of Japanese Essay2023

    • Author(s)
      Sayaka Nakamoto and Kazutaka Shimada
    • Organizer
      Proceedings of the 24th International Conference on Artificial Intelligence in Education, AIED 2023, Late Breaking Results, pp. 652-658, 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Detecting speech recognition errors using topic information and BERT2023

    • Author(s)
      Masaaki Yokoyama and Kazutaka Shimada
    • Organizer
      Proceedings of 13th International Conference on Smart Computing and Artificial Intelligence (SCAI 2023), pp. 400-405, 2023.
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Disfluency detection with context information from real utterances and generative utterances2023

    • Author(s)
      Hiroto Nakashima and Kazutaka Shimada
    • Organizer
      Proceedings of 13th International Conference on Smart Computing and Artificial Intelligence (SCAI 2023), pp. 462-467, 2023.
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Combination and Knowledge Extension of Pre-trained Language Model for Offensive Language Detection2023

    • Author(s)
      Zhenming Li and Kazutaka Shimada
    • Organizer
      Proceedings of 16th International Conference on E-Service and Knowledge Management (ESKM 2023), pp. 82-87, 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] マルチタスク学習の枠組みを用いた複数の評価観点を擁するレビューデータの評価値推定2023

    • Author(s)
      竹尾 匡貴, 川嵜 慎乃介, 嶋田 和孝
    • Organizer
      電子情報通信学会 信学技報 (言語理解とコミュニケーション研究会), vol. 123, no. 176, NLC2023-4, pp. 18-23
    • Related Report
      2023 Annual Research Report
  • [Presentation] Annotation and multi-modal methods for quality assessment of multi-party discussion2022

    • Author(s)
      Tsukasa Shiota and Kazutaka Shimada
    • Organizer
      Proceedings of PACLIC36
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] Combining Pre-Trained Language Models and Features for Offensive Language Detection2022

    • Author(s)
      Zhenming Li and Kazutaka Shimada
    • Organizer
      Proceedings of IIAI AAI 2022-Winter
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] 前後文脈を用いた対話文の言い淀み検出2022

    • Author(s)
      中島 寛人, 嶋田 和孝
    • Organizer
      電子情報通信学会 NLC研究会
    • Related Report
      2022 Research-status Report
  • [Presentation] 対話文における双方向文脈補完を用いた言い淀み検出2022

    • Author(s)
      中島 寛人, 嶋田 和孝
    • Organizer
      電子情報通信学会九州支部, 第30回学生会講演会
    • Related Report
      2022 Research-status Report
  • [Presentation] 機械学習モデルを用いたKyutechコーパスのトピック分類2022

    • Author(s)
      川嵜 慎乃介, 嶋田 和孝
    • Organizer
      電子情報通信学会 NLC研究会
    • Related Report
      2022 Research-status Report
  • [Presentation] 複数の議論コーパスを利用した談話行為推定2022

    • Author(s)
      米満 駿甫, 嶋田 和孝
    • Organizer
      2022年度 人工知能学会全国大会(第36回)
    • Related Report
      2022 Research-status Report
  • [Presentation] Discussion Structure Prediction Based on Two-step Method2021

    • Author(s)
      Takumi Himeno and Kazutaka Shimada
    • Organizer
      Proceedings of Recent Advances in Natural Language Processing, pp. 543-551
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Corpus construction for topic-based summarization of multi-party conversation2021

    • Author(s)
      Yuri Nakayama, Tsukasa Shiota, Kazutaka Shimada
    • Organizer
      Proceedings of the International Conference on Asian Language Processing (IALP), pp. 229-234
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 議論の分析とファシリテーションのための可視化ツールの構築2021

    • Author(s)
      西山 空良, 嶋田 和孝
    • Organizer
      電子情報通信学会, HCGシンポジウム2021, I-2-2
    • Related Report
      2021 Research-status Report
  • [Presentation] 複数人対話におけるトピック単位の要約データの構築とその要約2021

    • Author(s)
      中山 友梨, 塩田 宰, 嶋田 和孝
    • Organizer
      電子情報通信学会, NLC研究会, NLC2021-4, pp. 19-24, 2021
    • Related Report
      2021 Research-status Report
  • [Presentation] マルチモーダル情報を用いた複数人議論の品質評価2021

    • Author(s)
      塩田 宰,嶋田 和孝
    • Organizer
      人工知能学会, 第91回 言語・音声理解と対話処理研究会, pp. 116-121
    • Related Report
      2020 Research-status Report
  • [Presentation] 複数人議論における発話間の関係を対象とした関係分類2021

    • Author(s)
      姫野拓未, 嶋田和孝
    • Organizer
      言語処理学会第27回年次大会, NLP2021, P5-11
    • Related Report
      2020 Research-status Report
  • [Presentation] 複数人議論における対話的役割分類モデルの比較2021

    • Author(s)
      荻野 奈津実, 姫野 拓未, 嶋田 和孝
    • Organizer
      火の国シンポジウム2021, A1-3
    • Related Report
      2020 Research-status Report
  • [Presentation] Leader Identification Using Multimodal Information in Multi-party Conversations2020

    • Author(s)
      Tsukasa Shiota, Kouki Honda, Kazutaka Shimada, and Takeshi Saitoh
    • Organizer
      Proceedings of the International Conference on Asian Language Processing (IALP), P1-2, pp. 7-12
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] The Discussion Corpus toward Argumentation Quality Assessment in Multi-Party Conversation2020

    • Author(s)
      Tsukasa Shiota and Kazutaka Shimada
    • Organizer
      Proceedings of the 9th International Conference on Learning Technologies and Learning Environments
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Relation Identification Using Dialogical Features in Multi-Party Conversation2020

    • Author(s)
      Taskumi Himeno and Kazutaka Shimada
    • Organizer
      Proceedings of the 8th International Symposium on Applied Engineering and Sciences, C-O2-02
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Detection of Lying Situations in Liar Corpus2020

    • Author(s)
      Shohei Takabatake, Kazutaka Shimada, and Takeshi Saitoh
    • Organizer
      Proceedings of the 8th International Symposium on Applied Engineering and Sciences, C-O2-04
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Don't beat a dead horse: Recognizing a person who returns to a done-deal in a multi-party conversation2020

    • Author(s)
      Shunsuke Yonemitsu and Kazutaka Shimada
    • Organizer
      Proceedings of the 8th International Conference on Smart Computing and Artificial Intelligence
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Remarks] Kyutechコーパス・Kyutechディベートコーパス

    • URL

      http://www.pluto.ai.kyutech.ac.jp/~shimada/resources.html

    • Related Report
      2023 Annual Research Report
  • [Remarks] Kyutechコーパス/Kyuetchディベートコーパス

    • URL

      http://www.pluto.ai.kyutech.ac.jp/~shimada/resources.html

    • Related Report
      2022 Research-status Report
  • [Remarks] Kyutechコーパス

    • URL

      http://www.pluto.ai.kyutech.ac.jp/~shimada/resources.html

    • Related Report
      2021 Research-status Report 2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi