Fine-grained Conversational Decoding via Isotropic and Proximal Search

Yuxuan Yao, Han Wu, Qiling Xu, Linqi Song


Abstract
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 SimDRC that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed 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 significantly 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.
Anthology ID:
2023.emnlp-main.5
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–70
Language:
URL:
https://aclanthology.org/2023.emnlp-main.5
DOI:
10.18653/v1/2023.emnlp-main.5
Bibkey:
Cite (ACL):
Yuxuan Yao, Han Wu, Qiling Xu, and Linqi Song. 2023. Fine-grained Conversational Decoding via Isotropic and Proximal Search. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 58–70, Singapore. Association for Computational Linguistics.
Cite (Informal):
Fine-grained Conversational Decoding via Isotropic and Proximal Search (Yao et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.5.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.5.mp4