Fine-grained Conversational Decoding via Isotropic and Proximal Search

Yuxuan YAO, Han Wu, Qiling Xu, Linqi Song

Submission Type: Regular Short Paper

Submission Track: Dialogue and Interactive Systems

Submission Track 2: Natural Language Generation

Keywords: text generation; dialogue system; decoding strategy

TL;DR: A fine-grained decoding strategy for dialogue response generation

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.

Submission Number: 1736