Generative Knowledge Selection for Knowledge-Grounded Dialogues

Abstract

Knowledge selection is the key in knowledgegrounded 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-tosequence model. GENKS therefore captures intra-knowledge interaction inherently through attention mechanisms. Meanwhile, we devise a hyperlink mechanism to model the dialogueknowledge interactions explicitly. We conduct experiments on three benchmark datasets, and verify GENKS achieves the best results on both knowledge selection and response generation.

Stay grounded : incorporating knowledge in open-domain dialog

“…demonstrated this by implementing the MemNet concept(Dinan et al, 2019b) with BART Lotfi et al (2021). proposed an unsupervised knowledge selection method based on BART, which back-propagates the generation loss into a knowledge fusion module to train the selector Sun et al (2023a). used a fully generative approach augmented by explicit dialogue-knowledge connections, which generates the selected knowledge's identifier before the response.…”