Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems

TL;DR

This paper introduces a dual-feedback retriever-generator architecture for task-oriented dialogue systems, improving knowledge retrieval efficiency by using generator feedback as pseudo-labels, leading to better performance on benchmark datasets.

Contribution

It presents a novel dual-feedback mechanism that trains a retriever using generator feedback, addressing scalability issues in knowledge retrieval for dialogue systems.

Findings

Outperforms existing methods on three benchmark datasets

Effective use of generator feedback as pseudo-labels for retriever training

Enhances scalability and relevance in knowledge retrieval for dialogue systems

Abstract

Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests. However, current approaches generally integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases. Taking inspiration from open-domain question answering, we propose a retriever-generator architecture that harnesses a retriever to retrieve pertinent knowledge and a generator to generate system responses.~Due to the lack of retriever training labels, we propose relying on feedback from the generator as pseudo-labels to train the retriever. To achieve this, we introduce a dual-feedback mechanism that generates both positive and negative feedback based on the output of the generator. Our method demonstrates superior performance in task-oriented dialogue tasks, as evidenced by experimental results on three benchmark datasets.