Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2310.08130 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915171784458240 |
|---|---|
| author | Yao, Yuxuan Wu, Han Xu, Qiling Song, Linqi |
| author_facet | Yao, Yuxuan Wu, Han Xu, Qiling Song, Linqi |
| contents | General-purpose text decoding approaches are usually adopted for dialogue response generation. Although the quality of the generated responses can be improved with dialogue-specific encoding methods, conversational decoding methods are still under-explored. Inspired by \citet{wu2023learning} that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed \textit{isotropic and proximal search (IPS)}. Our method is designed to generate the semantic-concentrated response, while still maintaining informativeness and discrimination against the context. Experiments show that our approach outperforms existing decoding strategies in the dialogue field across both automatic and human evaluation metrics. More in-depth analyses further confirm the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08130 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fine-grained Conversational Decoding via Isotropic and Proximal Search Yao, Yuxuan Wu, Han Xu, Qiling Song, Linqi Computation and Language General-purpose text decoding approaches are usually adopted for dialogue response generation. Although the quality of the generated responses can be improved with dialogue-specific encoding methods, conversational decoding methods are still under-explored. Inspired by \citet{wu2023learning} that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed \textit{isotropic and proximal search (IPS)}. Our method is designed to generate the semantic-concentrated response, while still maintaining informativeness and discrimination against the context. Experiments show that our approach outperforms existing decoding strategies in the dialogue field across both automatic and human evaluation metrics. More in-depth analyses further confirm the effectiveness of our approach. |
| title | Fine-grained Conversational Decoding via Isotropic and Proximal Search |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2310.08130 |