Q-TOD: A Query-driven Task-oriented Dialogue System

TL;DR

Q-TOD is a novel dialogue system that uses natural language queries to retrieve relevant knowledge, improving domain adaptation and scalability in task-oriented dialogues.

Contribution

The paper introduces Q-TOD, a query-driven approach that decouples knowledge retrieval from response generation, enhancing adaptability and scalability in dialogue systems.

Findings

Q-TOD outperforms existing baselines on three datasets.

The system achieves state-of-the-art performance.

Query-based retrieval improves domain adaptation.

Abstract

Existing pipelined task-oriented dialogue systems usually have difficulties adapting to unseen domains, whereas end-to-end systems are plagued by large-scale knowledge bases in practice. In this paper, we introduce a novel query-driven task-oriented dialogue system, namely Q-TOD. The essential information from the dialogue context is extracted into a query, which is further employed to retrieve relevant knowledge records for response generation. Firstly, as the query is in the form of natural language and not confined to the schema of the knowledge base, the issue of domain adaption is alleviated remarkably in Q-TOD. Secondly, as the query enables the decoupling of knowledge retrieval from the generation, Q-TOD gets rid of the issue of knowledge base scalability. To evaluate the effectiveness of the proposed Q-TOD, we collect query annotations for three publicly available task-oriented dialogue datasets. Comprehensive experiments verify that Q-TOD outperforms strong baselines and establishes a new state-of-the-art performance on these datasets.