WEKO3
アイテム
Intention Detection Based on Siamese Neural Network With Triplet Loss
https://tokushima-u.repo.nii.ac.jp/records/2008307
https://tokushima-u.repo.nii.ac.jp/records/200830732d497a5-673a-43d9-a166-5d4ce977d075
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
access_8_82242.pdf (2.07 MB)
|
.png)
|
| Item type | 文献 / Documents(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2020-10-26 | |||||||||||||
| 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/10.1109/ACCESS.2020.2991484 | |||||||||||||
| 言語 | ja | |||||||||||||
| 関連名称 | 10.1109/ACCESS.2020.2991484 | |||||||||||||
| 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 | Intention Detection Based on Siamese Neural Network With Triplet Loss | |||||||||||||
| 言語 | en | |||||||||||||
| 著者 |
任, 福継
× 任, 福継
WEKO
401
× Xue, Siyuan
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Understanding the user's intention is an essential task for the spoken language understanding (SLU) module in the dialogue system, which further illustrates vital information for managing and generating future action and response. In this paper, we propose a triplet training framework based on the multiclass classification approach to conduct the training for the intention detection task. Precisely, we utilize a Siamese neural network architecture with metric learning to construct a robust and discriminative utterance feature embedding model. We modified the RMCNN model and fine-tuned BERT model as Siamese encoders to train utterance triplets from different semantic aspects. The triplet loss can effectively distinguish the details of two input data by learning a mapping from sequence utterances to a compact Euclidean space. After generating the mapping, the intention detection task can be easily implemented using standard techniques with pre-trained embeddings as feature vectors. Besides, we use the fusion strategy to enhance utterance feature representation in the downstream of intention detection task. We conduct experiments on several benchmark datasets of intention detection task: Snips dataset, ATIS dataset, Facebook multilingual task-oriented datasets, Daily Dialogue dataset, and MRDA dataset. The results illustrate that the proposed method can effectively improve the recognition performance of these datasets and achieves new state-of-the-art results on single-turn task-oriented datasets (Snips dataset, Facebook dataset), and a multi-turn dataset (Daily Dialogue dataset). | |||||||||||||
| 言語 | en | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Intention detection | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | BERT | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | RMCNN | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | triplet loss | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | fusion strategy | |||||||||||||
| 書誌情報 |
en : IEEE Access 巻 8, p. 82242-82254, 発行日 2020-04-30 |
|||||||||||||
| 収録物ID | ||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||
| 収録物識別子 | 21693536 | |||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | IEEE | |||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | ||||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ | |||||||||||||
| EID | ||||||||||||||
| 識別子 | 365942 | |||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
