External Knowledge Document Retrieval Strategy Based on Intention-guided and Meta-learning for Task-oriented Dialogues

Abstract

The external knowledge-enhanced task-oriented dialogues system is designed to cover the user requests beyond the predefined data base (DB) and application-specific interface (API). Existing methods mainly focus to improve the retrieval accuracy of the external knowledge but ignore the modeling of the entity-aware dialog intention, which cannot fast locate the document-level external API in the practical scenarios. Thus, this paper has introduced the entity-aware dialogue intention information and proposed a two-stage training method for the intention-guided knowledge document retrieval model, which can effectively enhance the retrieval accuracy of the Bi-encoder retrieval model in the task-based dialogue system. Besides, to further improve the generalization ability of the retrieval model based on the intention-guided, a meta-task based on the domain offset is constructed and make the Bi-encoder retrieval model get the more robust semantic representation through the meta-learning, which can improve the generalization capability of the model in invisible domains. Experimental results are shown to prove the correctness and effectiveness of the proposed strategy.