To diversify and enrich generated dialogue responses, knowledge-grounded dialogue has been investigated in recent years. The existing methods tackle the knowledge grounding challenge by retrieving the relevant sentences over a large corpus and augmenting the dialogues with explicit extra information. Despite their success, however, the existing works have drawbacks in inference efficiency. This paper proposes KnowExpert, a framework to bypass the explicit retrieval process and inject knowledge into the pre-trained language models with lightweight adapters and adapt to the knowledge-grounded dialogue task. To the best of our knowledge, this is the first attempt to tackle this challenge without retrieval in this task under an open-domain chit-chat scenario. The experimental results show that Knowexpert performs comparably with some retrieval-based baselines while being time-efficient in inference, demonstrating the effectiveness of our proposed method.
@article{arxiv.2105.06232,
title = {Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters},
author = {Yan Xu and Etsuko Ishii and Samuel Cahyawijaya and Zihan Liu and Genta Indra Winata and Andrea Madotto and Dan Su and Pascale Fung},
journal= {arXiv preprint arXiv:2105.06232},
year = {2022}
}
Comments
The first two authors contribute equally; Accepted in ACL 2022 DialDoc Workshop (Best Student Paper Award)