Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
This addresses the problem of generating more accurate and relevant dialogues in AI systems by efficiently using external knowledge, though it appears incremental as it builds on existing pre-trained models.
The paper tackled knowledge-grounded dialogue generation by proposing a method to integrate a knowledge selection module with pre-trained language models, achieving significant improvements over state-of-the-art methods on two benchmarks in automatic and human evaluations.
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.