Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation

Gunsoo Han, Daejin Jo, Daniel Wontae Nam, Eunseop Yoon, Taehwan Kwon, Seungeun Rho, Kyoung-Woon On, Chang D. Yoo, Sungwoong Kim

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Keywords: knowledge-grounded dialogue generation

Abstract: Knowledge-grounded dialogue generation requires first retrieving appropriate external knowledge based on a conversational context and then generating a response grounded on the retrieved knowledge. In general, these two sequential modules, a knowledge retriever and a response generator, have been separately trained in a supervised manner. However, obtaining intermediate labels of the ground-truth knowledge is expensive, especially in open-domain conversations. Latent variable modeling avoids this need for the labels. In this paper, we propose an efficient algorithm for this latent variable modeling that is able to leverage a large amount of dialogue data. Rather than directly training the complex retriever, we adapt a query generator with an off-the-shelf retriever, and the query generator and response generator are simultaneously trained over the latent variable of query. Moreover, we employ lower bound of the evidence as a training objective and modify it to robustly perform the joint training. Experimental results on diverse knowledge-grounded dialogue datasets show that the proposed algorithm significantly outperforms the supervised learning algorithm even without the use of the annotated knowledge while maintaining efficiency and scalability.

Submission Number: 1110