Back to Search Start Over

Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

Authors :
Wang, Yihe
Li, Yitong
Wang, Yasheng
Mi, Fei
Zhou, Pingyi
Wang, Xin
Liu, Jin
Jiang, Xin
Liu, Qun
Publication Year :
2022

Abstract

Real human conversation data are complicated, heterogeneous, and noisy, from which building open-domain dialogue systems remains a challenging task. In fact, such dialogue data still contains a wealth of information and knowledge, however, they are not fully explored. In this paper, we show existing open-domain dialogue generation methods that memorize context-response paired data with autoregressive or encode-decode language models underutilize the training data. Different from current approaches, using external knowledge, we explore a retrieval-generation training framework that can take advantage of the heterogeneous and noisy training data by considering them as "evidence". In particular, we use BERTScore for retrieval, which gives better qualities of the evidence and generation. Experiments over publicly available datasets demonstrate that our method can help models generate better responses, even such training data are usually impressed as low-quality data. Such performance gain is comparable with those improved by enlarging the training set, even better. We also found that the model performance has a positive correlation with the relevance of the retrieved evidence. Moreover, our method performed well on zero-shot experiments, which indicates that our method can be more robust to real-world data.<br />Comment: Accepted in COLING 2022

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2201.11367
Document Type :
Working Paper