Exploring Dense Retrieval for Dialogue Response Selection

13 Oct 2021  ·  Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Heyan Huang, Xian-Ling Mao ·

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and response candidates. While remarkably effective, these models also bring in a steep increase in computational cost. Consequently, such models can only be used as a re-rank module in practice. In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model. To push the limits of dense retrieval, we design an interaction layer upon the dense retrieval models and apply a set of tailor-designed learning strategies. Our model shows superiority over strong baselines on the conventional re-rank evaluation setting, which is remarkable given its efficiency. To verify the effectiveness of our approach in realistic scenarios, we also conduct full-rank evaluation, where the target is to select proper responses from a full candidate pool that may contain millions of candidates and evaluate them fairly through human annotations. Our proposed model notably outperforms pipeline baselines that integrate fast recall and expressive re-rank modules. Human evaluation results show that enlarging the candidate pool with nonparallel corpora improves response quality further.

PDF Abstract

Datasets


Introduced in the Paper:

RRS RRS Ranking Test

Used in the Paper:

Douban E-commerce

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here