• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2019 年度 実施状況報告書

Learning conversation agents for long-vision response generation in multi-round communications

研究課題

研究課題/領域番号 19K20345
研究機関徳島大学

研究代表者

康 シン  徳島大学, 大学院社会産業理工学研究部(理工学域), 助教 (80777350)

研究期間 (年度) 2019-04-01 – 2022-03-31
キーワードlong-vision conversation
研究実績の概要

The purpose of this research plan is to learn the long-vision conversation agents from scratch by allowing them to make sequential decisions in a multi-round communication. For these agents, the language ability, the self-concept identification ability, and the strategic conversation ability would be developed through three strategic communication games respectively.
In the first year, we have developed the basic language ability for the agents. Through a competing game of two communication agents, one agent is able to describe a given word with a simple natural language sentence. The generated sentences are syntactically and semantically reasonable, and can be well understood by human beings. And the other agent is able to read these generated sentence and to guess what the originally given word is.
The model for word-to-sentence interpretation and the model for sentence-to-word induction are based on two deep neural networks, respectively. These two models are trained side-by-side through a competing game, in which a correct round of interpretation-induction renders a positive feed back to encourage the models to make similar decisions in the future games while an incorrect round renders a negative feed back to encourage them to try other options in the future.
The developed language ability is found as the basis for the agents to describe their opinions for the other agents to infer those opinions from either similar agents or human beings.

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

The experiment of language ability development for long-vision conversation agents is done smoothly. The results suggest that the agents are able to interpret word into syntactically correct and semantically reasonable natural language sentences while at the same time are able to induce such sentences backward into words successfully.

今後の研究の推進方策

To learn long-vision conversation agents, we will continue to develop a self-concept identification ability and a strategic conversation ability for the agents as proposed in the research plan.
Specifically for this year, we will focus on developing the self-concept identification ability for the agents, by asking them to categorize everyone’s social identities and to recognize the commonality in those social identities as their self-concepts. The already learned encoder and decoder networks in the last year will be integrated into a new model with a categorization layer on top, in order to interpret and induce the identities of themselves and the others for a successful self-concept recognition.

  • 研究成果

    (29件)

すべて 2020 2019

すべて 雑誌論文 (1件) (うち国際共著 1件、 査読あり 1件) 学会発表 (28件) (うち国際学会 20件)

  • [雑誌論文] Toward action comprehension for searching: Mining actionable intents in query entities2019

    • 著者名/発表者名
      Kang Xin、Wu Yunong、Ren Fuji
    • 雑誌名

      Journal of the Association for Information Science and Technology

      巻: 71 ページ: 143~157

    • DOI

      10.1002/asi.24220

    • 査読あり / 国際共著
  • [学会発表] Environment recognition using robot camera2020

    • 著者名/発表者名
      Hiroaki Sumida, Fuji Ren, Shun Nishide, and Xin Kang
    • 学会等名
      The 5th IEEE International Conference on Big Data Analytics (IEEE ICBDA 2020)
    • 国際学会
  • [学会発表] A Chinese-Japanese Vowel Priority Lip Matching Scheme Based on Humanoid Robot Ren-Xin2020

    • 著者名/発表者名
      Zheng Liu, Xin Kang, Shun Nishide and Fuji Ren
    • 学会等名
      The 5th International Symposium on Artificial Intelligence and Robotics 2020 (ISAIR 2020)
    • 国際学会
  • [学会発表] A Fusion Model for Multi-label Emotion Classification Based on BERT and Topic Clustering2020

    • 著者名/発表者名
      Fei Ding, Xin Kang, Shun Nishide, Zhijin Guan and Fuji Ren
    • 学会等名
      The 5th International Symposium on Artificial Intelligence and Robotics 2020 (ISAIR 2020)
    • 国際学会
  • [学会発表] 神経力学モデルを用いたプリミティブの階層的学習2020

    • 著者名/発表者名
      野本 楓晟, 安田 伊慶, 西出 俊, 康 シン
    • 学会等名
      情報処理学会全国大会
  • [学会発表] リカレントニューラルネットワークを用いた未学習のコードからの楽譜生成2020

    • 著者名/発表者名
      真砂 光志, 西出 俊, 康 シン, 任 福継
    • 学会等名
      情報処理学会全国大会
  • [学会発表] 深層モデルを用いた画像系列の特徴量自己組織化と映像生成2020

    • 著者名/発表者名
      川野 真子, 西出 俊, 康 シン, 任 福継
    • 学会等名
      情報処理学会全国大会
  • [学会発表] ペンの持ち上げを考慮した神経力学モデルによる描画図形予測と生成2020

    • 著者名/発表者名
      久保野 雄亮, 西出 俊, 康 シン, 任 福継
    • 学会等名
      情報処理学会全国大会
  • [学会発表] ロボット教師における特定分野のQAシステムの構築2020

    • 著者名/発表者名
      門田 尚之, 康 シン, 西出 俊, 任 福継
    • 学会等名
      電子情報通信学会総合大会
  • [学会発表] ロボット教師における特定人物の音声の自動生成2020

    • 著者名/発表者名
      寺尾 渉吾, 康 シン, 西出 俊, 任 福継
    • 学会等名
      電子情報通信学会総合大会
  • [学会発表] 単語の感情属性を活かしたロボット教師の表情生成2020

    • 著者名/発表者名
      房登 淳平, 康 シン, 西出 俊, 任 福継
    • 学会等名
      電子情報通信学会総合大会
  • [学会発表] ロボット教師による特定分野の記述式問題の判定について2020

    • 著者名/発表者名
      山崎 直登, 康 シン, 西出 俊, 任 福継
    • 学会等名
      電子情報通信学会総合大会
  • [学会発表] Research on the Effect of Different Speech Segment Lengths on Speech Emotion Recognition Based on LSTM2019

    • 著者名/発表者名
      Zheng Liu, Fuji Ren, and Xin Kang
    • 学会等名
      The 9th International Workshop on Computer Science and Engineering (WCSE 2019)
    • 国際学会
  • [学会発表] Traffic Sign Recognition Based on Up-sampling Convolution2019

    • 著者名/発表者名
      Yitian Lu, Ping Jiang, Shun Nishide, Xin Kang, and Fuji Ren
    • 学会等名
      The 9th International Workshop on Computer Science and Engineering (WCSE 2019)
    • 国際学会
  • [学会発表] Feature Fusion Based on Neural Image Captioning with Spatial Attention2019

    • 著者名/発表者名
      Qingqing Lu, Xiaomei Zhang, Xin Kang, and Fuji Ren
    • 学会等名
      The 9th International Workshop on Computer Science and Engineering (WCSE 2019)
    • 国際学会
  • [学会発表] Position-Free Hand Gesture Recognition Using Single Shot MultiBox Detector Based Neural Network2019

    • 著者名/発表者名
      Jingwei Tang, Xingtian Yao, Xin Kang, Shun Nishide, and Fuji Ren
    • 学会等名
      2019 IEEE International Conference on Mechatronics and Automation (ICMA)
    • 国際学会
  • [学会発表] Text Detection for Natural Scene based on MobileNet V2 and U-Net2019

    • 著者名/発表者名
      Fu, Kangwei, Ling Sun, Xin Kang, and Fuji Ren
    • 学会等名
      2019 IEEE International Conference on Mechatronics and Automation (ICMA)
    • 国際学会
  • [学会発表] Face and Gender Recognition System Based on Convolutional Neural networks2019

    • 著者名/発表者名
      Zhou, Yuxiang, Hongjun Ni, Fuji Ren, and Xin Kang
    • 学会等名
      2019 IEEE International Conference on Mechatronics and Automation (ICMA)
    • 国際学会
  • [学会発表] Building Label-Balanced Emotion Corpus Based On Active Learning for Text Emotion Classification2019

    • 著者名/発表者名
      Xuefeng Shi, Xin Kang, Ping Liao, and Fuji Ren
    • 学会等名
      The 4th International Symposium on Artificial Intelligence and Robotics (ISAIR2019)
    • 国際学会
  • [学会発表] Capture Important Information for Reading andReasoning by A Two-Pass Attention Mechanism in Dynamic Memory Network2019

    • 著者名/発表者名
      Zheng Zhou, Xin Kang, Shun Nishide, and Fuji Ren
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] Text multi-label sentiment analysis based on Bi-LSTM2019

    • 著者名/発表者名
      Junlin Hu, Xin Kang, Shun Nishide, and Fuji Ren
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] ExploringUncertain Samples through Active Learning To Enhance Text Emotion Classification2019

    • 著者名/発表者名
      Rongyu Dou, Nishide Shun, Fuji Ren, and Xin Kang
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] Object detection based on SSD-ResNet2019

    • 著者名/発表者名
      Xin Lu, Xin Kang, Shun Nishide, and Fuji Ren
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] Character action recognition based on deep convolutional neural network and action sequence2019

    • 著者名/発表者名
      Jiaen Li, Fuji Ren, Shun Nishide, and Xin Kang
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] Constructing a Fundamental DevelopmentalDrawing Learning Model Using an Arm Robot2019

    • 著者名/発表者名
      Ryosuke Yasumura, Shun Nishide, Xin Kang, and Fuji Ren
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] Investigating voice features for Speech emotion recognition based on four kinds of machine learning methods2019

    • 著者名/発表者名
      Haiyan Chen, Zheng Liu, Xin Kang, Shun Nishide, and Fuji Ren
    • 学会等名
      The 6th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS2019)
    • 国際学会
  • [学会発表] TUA1 at the NTCIR-14 STC-3 Task2019

    • 著者名/発表者名
      Zhou, Yangyang, Zheng Liu, Xin Kang, Yunong Wu, and Fuji Ren
    • 学会等名
      The 14th NTCIR Conference
    • 国際学会
  • [学会発表] Tua1 at imageclef 2019 vqa-med: A classification and generation model based on transfer learning2019

    • 著者名/発表者名
      Zhou, Yangyang, Xin Kang, and Fuji Ren
    • 学会等名
      Conference and Labs of the Evaluation Form (CLEF) 2019
    • 国際学会
  • [学会発表] TUA1 at the TREC 2019: Deep Learning Track2019

    • 著者名/発表者名
      Yun Gao, Haitao Yu, Xin Kang, and Fuji Ren
    • 学会等名
      The 28th Text Retrieval Conference (TREC 2019)
    • 国際学会

URL: 

公開日: 2021-01-27  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi