From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue

Authors

  • Zeyuan Ding School of Computer Science and Technology, Dalian University of Technology, China
  • Zhihao Yang School of Computer Science and Technology, Dalian University of Technology, China
  • Ling Luo School of Computer Science and Technology, Dalian University of Technology, China
  • Yuanyuan Sun School of Computer Science and Technology, Dalian University of Technology, China
  • Hongfei Lin School of Computer Science and Technology, Dalian University of Technology, China

DOI:

https://doi.org/10.1609/aaai.v38i16.29745

Keywords:

NLP: Conversational AI/Dialog Systems, NLP: Question Answering

Abstract

Retrieving appropriate records from the external knowledge base to generate informative responses is the core capability of end-to-end task-oriented dialogue systems (EToDs). Most of the existing methods additionally train the retrieval model or use the memory network to retrieve the knowledge base, which decouples the knowledge retrieval task from the response generation task, making it difficult to jointly optimize and failing to capture the internal relationship between the two tasks. In this paper, we propose a simple and unified generative model for task-oriented dialogue systems, which recasts the EToDs task as a single sequence generation task and uses maximum likelihood training to train the two tasks in a unified manner. To prevent the generation of non-existent records, we design the prefix trie to constrain the model generation, which ensures consistency between the generated records and the existing records in the knowledge base. Experimental results on three public benchmark datasets demonstrate that our method achieves robust performance on generating system responses and outperforms the baseline systems. To facilitate future research in this area, the code is available at https://github.com/dzy1011/Uni-ToD.

Published

2024-03-24

How to Cite

Ding, Z., Yang, Z., Luo, L., Sun, Y., & Lin, H. (2024). From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17907-17914. https://doi.org/10.1609/aaai.v38i16.29745

Issue

Section

AAAI Technical Track on Natural Language Processing I