Contextual Knowledge Learning For Dialogue Generation
This work addresses the challenge of generating more relevant and high-quality responses in dialogue systems, which is incremental as it builds on existing methods for context and knowledge integration.
The paper tackles the problem of incorporating conversational context and external knowledge into dialogue generation models by proposing a Contextual Knowledge Learning (CKL) approach that uses latent vectors for fine-grained weighting, resulting in significant improvements over six strong baselines and robustness with reduced training data.
Incorporating conversational context and knowledge into dialogue generation models has been essential for improving the quality of the generated responses. The context, comprising utterances from previous dialogue exchanges, is used as a source of content for response generation and as a means of selecting external knowledge. However, to avoid introducing irrelevant content, it is key to enable fine-grained scoring of context and knowledge. In this paper, we present a novel approach to context and knowledge weighting as an integral part of model training. We guide the model training through a Contextual Knowledge Learning (CKL) process which involves Latent Vectors for context and knowledge, respectively. CKL Latent Vectors capture the relationship between context, knowledge, and responses through weak supervision and enable differential weighting of context utterances and knowledge sentences during the training process. Experiments with two standard datasets and human evaluation demonstrate that CKL leads to a significant improvement compared with the performance of six strong baseline models and shows robustness with regard to reduced sizes of training sets.