トップ研究者を探すLearning conversation agents for long-vision response generation in multi-round communications

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

KAKEN 科学研究費助成事業データベース で見る
研究課題番号 KAKENHI-PROJECT-19K20345
研究種目 若手研究
研究分野
研究機関 徳島大学
代表研究者 康 シン
研究期間 開始年月日 2019/4/1
研究期間 終了年度 2021
研究ステータス 完了 (2021/4/1)
配分額(合計) 4,160,000 (直接経費 :3,200,000、間接経費 :960,000)
配分額(履歴) 2021年度:1,040,000 (直接経費 :800,000、間接経費 :240,000)
2020年度:1,040,000 (直接経費 :800,000、間接経費 :240,000)
2019年度:2,080,000 (直接経費 :1,600,000、間接経費 :480,000)
キーワード 対話生成
対話完成程度
対話完成効率
対話ユーザー満足度
long-vision conversation
dialogue topic tagging
neuro-symbolic AI
DialogQuality Evaluation
response generation
language ability
self-concept identifying
strategic conversation

研究成果

[学会発表] TUA1 at the NTCIR-16 DialEval-2 Task

Fei Ding, Xin Kang, Yunong Wu, Fuji Ren 2022

[学会発表] Creating a Japanese dialogue corpus with multi-level topic analysis

Yuma Komoto, Xin Kang and Fuji Ren 2022

[学会発表] Improvement of Japanese Text Emotion Analysis by Active Learning Using Transformers Language Model

Tatsuya Ikegami, Xin Kang and Fuji Ren 2022

[学会発表] Classification of Steel Strip Surface Defects Based on Optimized ResNet18

Hao Zhuangzhuang, Fuji Ren, Xin Kang, Ni Hongjun, Lv Shuaishuai and Wang Hui 2021

[雑誌論文] The AI Development Through Transforming Tacit Knowledge to Explicit Knowledge of Nurses' Dialogue for Patients with Dementia

Hirokazu Ito, Kazuyuki Matsumoto, Xin Kang, Tetsuya Tanioka, Yuko Yasuhara, Rozzano De Castro Locsin and Fuji Ren 2021

[学会発表] Prediction and Generation of Multiple Complex Drawing Figures From Partial Drawing Sequences

Kubono Yusuke, Shun Nishide, Xin Kang and Fuji Ren 2021

[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

門田 尚之, 康 シン, 西出 俊, 任 福継 2020

[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

房登 淳平, 康 シン, 西出 俊, 任 福継 2020

[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

久保野 雄亮, 西出 俊, 康 シン, 任 福継 2020

[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

野本 楓晟, 安田 伊慶, 西出 俊, 康 シン 2020

[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

真砂 光志, 西出 俊, 康 シン, 任 福継 2020

[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

川野 真子, 西出 俊, 康 シン, 任 福継 2020

[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

寺尾 渉吾, 康 シン, 西出 俊, 任 福継 2020

[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

山崎 直登, 康 シン, 西出 俊, 任 福継 2020

[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

門田 尚之, 任 福継, 西出 俊, 康 シン 2020

[学会発表] Tweet日本語感情コーパスに対するBERTの効果の検証

池上 達也, 任 福継, 西出 俊, 康 シン 2020

[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

寺尾 渉吾, 任 福継, 西出 俊, 康 シン 2020

[学会発表] A Chinese-Japanese Vowel Priority Lip Matching Scheme Based on Humanoid Robot Ren-Xin

Zheng Liu, Xin Kang, Shun Nishide and Fuji Ren 2020

[学会発表] TUA1 at the NTCIR-15 DialEval-1 Task

Xin Kang, Yunong Wu and Fuji Ren 2020

[雑誌論文] DFF-ResNet: An insect pest recognition model based on residual networks

Liu Wenjie、Wu Guoqing、Ren Fuji、Kang Xin 2020

[雑誌論文] Active learning with complementary sampling for instructing class-biased multi-label text emotion classification

Kang Xin、Shi Xuefeng、Wu Yunong、Ren Fuji 2020

[学会発表] A fusion model for multi-label emotion classification based on BERT and topic clustering

Fei Ding, Xin Kang, Shun Nishide, Guan Zhijin and Fuji Ren 2020

[雑誌論文] Surface defect detection of steel strips based on classification priority YOLOv3-dense network

Zhang Jiaqiao、Kang Xin、Ni Hongjun、Ren Fuji 2020

[学会発表] Examination to develop the artificial intelligence through transforming tacit knowledge of nurses' dialogue for patients with dementia towards explicit knowledge

Hirokazu Ito, Kazuyuki Matsumoto, Xin Kang, Tetsuya Tanioka, Yuko Yasuhara, Rozzano De Castro Locsin and Fuji Ren 2020

[学会発表] Speech emotion recognition based on data enhancement in time-frequency domain

LI Qianqian, Fuji Ren, Shen Xiaoyan and Xin Kang 2020

[学会発表] Environment recognition using robot camera

Hiroaki Sumida, Fuji Ren, Shun Nishide, and Xin Kang 2020

[学会発表] A Fusion Model for Multi-label Emotion Classification Based on BERT and Topic Clustering

Fei Ding, Xin Kang, Shun Nishide, Zhijin Guan and Fuji Ren 2020

[学会発表] Construction of emergency medical support system based on understanding dialect intention

Kyoya Abe, Fuji Ren, Shun Nishide and Xin Kang 2020

[雑誌論文] Vowel priority lip matching scheme and similarity evaluation model based on humanoid robot Ren-Xin

Liu Zheng、Kang Xin、Nishide Shun、Ren Fuji 2020

[学会発表] Collaborative filtering recommendation algorithm based on bisecting K-means clustering

Liu Jia, Xin Kang, Shun Nishide and Fuji Ren 2020

[学会発表] Gait recognition in real environment using gait energy image generated by Mask R-CNN

Shota Inui, Fuji Ren, Shun Nishide and Xin Kang 2020

[学会発表] Feature Fusion Based on Neural Image Captioning with Spatial Attention

Qingqing Lu, Xiaomei Zhang, Xin Kang, and Fuji Ren 2019

[学会発表] Traffic Sign Recognition Based on Up-sampling Convolution

Yitian Lu, Ping Jiang, Shun Nishide, Xin Kang, and Fuji Ren 2019

[学会発表] Character action recognition based on deep convolutional neural network and action sequence

Jiaen Li, Fuji Ren, Shun Nishide, and Xin Kang 2019

[学会発表] Building Label-Balanced Emotion Corpus Based On Active Learning for Text Emotion Classification

Xuefeng Shi, Xin Kang, Ping Liao, and Fuji Ren 2019

[学会発表] Investigating voice features for Speech emotion recognition based on four kinds of machine learning methods

Haiyan Chen, Zheng Liu, Xin Kang, Shun Nishide, and Fuji Ren 2019

[学会発表] Capture Important Information for Reading andReasoning by A Two-Pass Attention Mechanism in Dynamic Memory Network

Zheng Zhou, Xin Kang, Shun Nishide, and Fuji Ren 2019

[学会発表] TUA1 at the NTCIR-14 STC-3 Task

Zhou, Yangyang, Zheng Liu, Xin Kang, Yunong Wu, and Fuji Ren 2019

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

Kang Xin、Wu Yunong、Ren Fuji 2019

[学会発表] Constructing a Fundamental DevelopmentalDrawing Learning Model Using an Arm Robot

Ryosuke Yasumura, Shun Nishide, Xin Kang, and Fuji Ren 2019

[学会発表] Position-Free Hand Gesture Recognition Using Single Shot MultiBox Detector Based Neural Network

Jingwei Tang, Xingtian Yao, Xin Kang, Shun Nishide, and Fuji Ren 2019

[学会発表] ExploringUncertain Samples through Active Learning To Enhance Text Emotion Classification

Rongyu Dou, Nishide Shun, Fuji Ren, and Xin Kang 2019

[学会発表] Tua1 at imageclef 2019 vqa-med: A classification and generation model based on transfer learning

Zhou, Yangyang, Xin Kang, and Fuji Ren 2019

[学会発表] TUA1 at the TREC 2019: Deep Learning Track

Yun Gao, Haitao Yu, Xin Kang, and Fuji Ren 2019

[学会発表] Text multi-label sentiment analysis based on Bi-LSTM

Junlin Hu, Xin Kang, Shun Nishide, and Fuji Ren 2019

[学会発表] Text Detection for Natural Scene based on MobileNet V2 and U-Net

Fu, Kangwei, Ling Sun, Xin Kang, and Fuji Ren 2019

[学会発表] Research on the Effect of Different Speech Segment Lengths on Speech Emotion Recognition Based on LSTM

Zheng Liu, Fuji Ren, and Xin Kang 2019

[学会発表] Object detection based on SSD-ResNet

Xin Lu, Xin Kang, Shun Nishide, and Fuji Ren 2019

[学会発表] Face and Gender Recognition System Based on Convolutional Neural networks

Zhou, Yuxiang, Hongjun Ni, Fuji Ren, and Xin Kang 2019