WEKO3
アイテム
Response type selection for chat-like spoken dialog systems based on LSTM and multi-task learning
https://tokushima-u.repo.nii.ac.jp/records/2009570
https://tokushima-u.repo.nii.ac.jp/records/2009570f699e7a1-dcd8-4392-aa26-b7cb8268f899
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
Item type | 文献 / Documents(1) | |||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
公開日 | 2022-02-28 | |||||||||||||||||
アクセス権 | ||||||||||||||||||
アクセス権 | open access | |||||||||||||||||
資源タイプ | ||||||||||||||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||||||
資源タイプ | journal article | |||||||||||||||||
出版社版DOI | ||||||||||||||||||
識別子タイプ | DOI | |||||||||||||||||
関連識別子 | https://doi.org/10.1016/j.specom.2021.07.003 | |||||||||||||||||
言語 | ja | |||||||||||||||||
関連名称 | 10.1016/j.specom.2021.07.003 | |||||||||||||||||
出版タイプ | ||||||||||||||||||
出版タイプ | VoR | |||||||||||||||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||||||
タイトル | ||||||||||||||||||
タイトル | Response type selection for chat-like spoken dialog systems based on LSTM and multi-task learning | |||||||||||||||||
言語 | en | |||||||||||||||||
著者 |
オオタ, ケンゴ
× オオタ, ケンゴ
× 西村, 良太
WEKO
942
× 北岡, 教英 |
|||||||||||||||||
抄録 | ||||||||||||||||||
内容記述タイプ | Abstract | |||||||||||||||||
内容記述 | We propose a method of automatically selecting appropriate responses in conversational spoken dialog systems by explicitly determining the correct response type that is needed first, based on a comparison of the user’s input utterance with many other utterances. Response utterances are then generated based on this response type designation (back channel, changing the topic, expanding the topic, etc.). This allows the generation of more appropriate responses than conventional end-to-end approaches, which only use the user’s input to directly generate response utterances. As a response type selector, we propose an LSTM-based encoder–decoder framework utilizing acoustic and linguistic features extracted from input utterances. In order to extract these features more accurately, we utilize not only input utterances but also response utterances in the training corpus. To do so, multi-task learning using multiple decoders is also investigated. To evaluate our proposed method, we conducted experiments using a corpus of dialogs between elderly people and an interviewer. Our proposed method outperformed conventional methods using either a point-wise classifier based on Support Vector Machines, or a single-task learning LSTM. The best performance was achieved when our two response type selectors (one trained using acoustic features, and the other trained using linguistic features) were combined, and multi-task learning was also performed. |
|||||||||||||||||
言語 | en | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | Spoken dialog system | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | Response type selection | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | Encoder–decoder model | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | Multi-task learning | |||||||||||||||||
書誌情報 |
en : Speech Communication 巻 133, p. 23-30, 発行日 2021-07-15 |
|||||||||||||||||
収録物ID | ||||||||||||||||||
収録物識別子タイプ | ISSN | |||||||||||||||||
収録物識別子 | 01676393 | |||||||||||||||||
収録物ID | ||||||||||||||||||
収録物識別子タイプ | NCID | |||||||||||||||||
収録物識別子 | AA10630135 | |||||||||||||||||
収録物ID | ||||||||||||||||||
収録物識別子タイプ | NCID | |||||||||||||||||
収録物識別子 | AA11541653 | |||||||||||||||||
出版者 | ||||||||||||||||||
出版者 | Elsevier | |||||||||||||||||
言語 | en | |||||||||||||||||
権利情報 | ||||||||||||||||||
言語 | en | |||||||||||||||||
権利情報 | This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
|||||||||||||||||
EID | ||||||||||||||||||
識別子 | 376748 | |||||||||||||||||
識別子タイプ | URI | |||||||||||||||||
言語 | ||||||||||||||||||
言語 | eng |