Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
This work addresses the challenge of scaling dialogue systems to large knowledge bases, which is crucial for improving response accuracy in task-oriented applications.
The paper tackles the problem of identifying relevant knowledge base entities for end-to-end task-oriented dialogue systems by proposing a novel filtering technique that respects KB structure and uses an auxiliary loss, achieving state-of-the-art performance on three public datasets.
End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for an utterance is crucial for response generation. Existing state of the art scales to large KBs by softly filtering over irrelevant KB information. In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record. and, (2) an auxiliary loss that helps in separating contextually unrelated KB information. We also propose a new metric -- multiset entity F1 which fixes a correctness issue in the existing entity F1 metric. Experimental results on three publicly available task-oriented dialog datasets show that our proposed approach outperforms existing state-of-the-art models.