Generative Knowledge Selection for Knowledge-Grounded Dialogues
This addresses a key bottleneck in improving dialogue systems by enhancing knowledge selection, though it is an incremental advancement over existing classification methods.
The paper tackles the problem of selecting appropriate knowledge snippets for knowledge-grounded dialogues by proposing a generative approach called GenKS, which achieves state-of-the-art results on three benchmark datasets for both knowledge selection and response generation.
Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. Previous studies mainly employ the classification approach to classify each candidate snippet as "relevant" or "irrelevant" independently. However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets. Moreover, they lack modeling of the discourse structure of dialogue-knowledge interactions. We propose a simple yet effective generative approach for knowledge selection, called GenKS. GenKS learns to select snippets by generating their identifiers with a sequence-to-sequence model. GenKS therefore captures intra-knowledge interaction inherently through attention mechanisms. Meanwhile, we devise a hyperlink mechanism to model the dialogue-knowledge interactions explicitly. We conduct experiments on three benchmark datasets, and verify GenKS achieves the best results on both knowledge selection and response generation.