Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

TL;DR

This paper introduces a method for knowledge-grounded dialogue generation that combines a knowledge selection module with pre-trained language models, improving response quality by jointly optimizing knowledge selection and response generation.

Contribution

It proposes an unsupervised approach to jointly optimize knowledge selection and response generation in pre-trained language models for dialogue systems.

Findings

Significant improvement over state-of-the-art in automatic evaluation.

Enhanced human judgment scores.

Effective knowledge selection in dialogue generation.

Abstract

We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with a knowledge selection module, and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues. Empirical results on two benchmarks indicate that our model can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.