Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog

TL;DR

This paper introduces MAKER, a multi-grained knowledge retriever for end-to-end task-oriented dialog systems, which decouples retrieval from response generation and improves knowledge retrieval accuracy, especially with large-scale databases.

Contribution

The paper proposes a novel decoupled retrieval approach with an entity and attribute selector, trained via a distillation objective, enhancing retrieval performance over existing methods.

Findings

Outperforms existing retrieval methods on three benchmarks

Effective with both small and large-scale knowledge bases

Code is publicly available for reproducibility

Abstract

Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses. Most existing systems blend knowledge retrieval with response generation and optimize them with direct supervision from reference responses, leading to suboptimal retrieval performance when the knowledge base becomes large-scale. To address this, we propose to decouple knowledge retrieval from response generation and introduce a multi-grained knowledge retriever (MAKER) that includes an entity selector to search for relevant entities and an attribute selector to filter out irrelevant attributes. To train the retriever, we propose a novel distillation objective that derives supervision signals from the response generator. Experiments conducted on three standard benchmarks with both small and large-scale knowledge bases demonstrate that our retriever performs knowledge retrieval more effectively than existing methods. Our code has been made publicly available.\footnote{https://github.com/18907305772/MAKER}