| Presentation | 2020-02-17 Facilitator Identification Using Multimodal Information in Multi-party Conversation Kouki Honda, Tukasa Shiota, Kazutaka Shimada, Takeshi Saitoh, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Predicting roles of participants in a conversation is one of the most important tasks for conversation understanding. In this paper, we propose a prediction model of facilitators in conversations. A previous study has handled verbal features for the facilitator prediction task. However, non-verbal features are also important elements for the prediction. Therefore, we introduce non-verbal features into the prediction model. We utilize two types of non-verbal features: motion features and voice features. The motion features are based on face information and body information. The voice features are based on prosodic information. In the experiment, we compare our model with a verbal feature-based model. The experimental result shows the effectiveness of our method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Multi-party Conversation / Multimodal / Role Recognition / Facilitator |
| Paper # | NLC2019-41 |
| Date of Issue | 2020-02-09 (NLC) |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2020/2/16(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Seikei University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Integration of verbal and non-verbal information |
| Chair | Takeshi Sakaki(Hottolink) |
| Vice Chair | Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Kazutaka Shimada(Kyushu Inst. of Tech.) |
| Secretary | Mitsuo Yoshida(Ryukoku Univ.) / Kazutaka Shimada(NTT) |
| Assistant | Takeshi Kobayakawa(NHK) / Hiroki Sakaji(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Facilitator Identification Using Multimodal Information in Multi-party Conversation |
| Sub Title (in English) | |
| Keyword(1) | Multi-party Conversation |
| Keyword(2) | Multimodal |
| Keyword(3) | Role Recognition |
| Keyword(4) | Facilitator |
| 1st Author's Name | Kouki Honda |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 2nd Author's Name | Tukasa Shiota |
| 2nd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 3rd Author's Name | Kazutaka Shimada |
| 3rd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 4th Author's Name | Takeshi Saitoh |
| 4th Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| Date | 2020-02-17 |
| Paper # | NLC2019-41 |
| Volume (vol) | vol.119 |
| Number (no) | NLC-415 |
| Page | pp.pp.27-32(NLC), |
| #Pages | 6 |
| Date of Issue | 2020-02-09 (NLC) |