| Presentation | 2022-11-05 Estimation and Visualization of Learning Types for Class Dialogues Using Neural Network Model Sakuei Onishi, Hiromitsu Shiina, Tomohiko Yasumori, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In elementary school classes, lesson inspection activities have been conducted to improve classes, and feedback is important. In particular, there are many utterances such as teacher's explanation and promotion, questions, and children's answers, and there is a kind of dialogue. By analyzing this dialogue, it is possible to analyze the type of utterance of teachers and the state of learning of children, and to feedback the classification of learning to teachers. In addition to BERT and Transformer's methods, which enable us to grasp context, there is a GVT model that is used in dialogue response generation as a suitable model for conversation. In this study, in addition to the analysis by Bert, we propose a model that extends the GVT (Global Variational Transformer) model to consider the context for each teacher - child interlocutor, and analyze the type of learning from the dialogue. In addition, we are developing a system for visualizing the time series distribution of learning types in classes. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Reflection Activity / Speech Classfication Dialogue Analysis / BERT / Transormer / GVT / Visualization |
| Paper # | ET2022-38 |
| Date of Issue | 2022-10-29 (ET) |
| Conference Information | |
| Committee | ET |
|---|---|
| Conference Date | 2022/11/5(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Sessions for Young Researchers (Young Researcher Awards Selection), etc. |
| Chair | Kenji Watanabe(Hiroshimai Univ.) |
| Vice Chair | Hisayoshi Kunimune(Chiba Inst. of Tech.) |
| Secretary | Hisayoshi Kunimune(Mejiro Univ.) |
| Assistant | Kazuaki Yoshihara(Kinki Univ.) / Toru Kano(Tokyo University of Science) |
| Paper Information | |
| Registration To | Technical Committee on Educational Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimation and Visualization of Learning Types for Class Dialogues Using Neural Network Model |
| Sub Title (in English) | |
| Keyword(1) | Reflection Activity |
| Keyword(2) | Speech Classfication Dialogue Analysis |
| Keyword(3) | BERT |
| Keyword(4) | Transormer |
| Keyword(5) | GVT |
| Keyword(6) | Visualization |
| 1st Author's Name | Sakuei Onishi |
| 1st Author's Affiliation | Graduate School of Informatics(Okayama Unisersity of Science) |
| 2nd Author's Name | Hiromitsu Shiina |
| 2nd Author's Affiliation | Okayama Unisersity of Science(Okayama Unisersity of Science) |
| 3rd Author's Name | Tomohiko Yasumori |
| 3rd Author's Affiliation | Okayama Unisersity of Science(Okayama Univ. of Science) |
| Date | 2022-11-05 |
| Paper # | ET2022-38 |
| Volume (vol) | vol.122 |
| Number (no) | ET-241 |
| Page | pp.pp.47-54(ET), |
| #Pages | 8 |
| Date of Issue | 2022-10-29 (ET) |