@article{Liu2023, 
author = {Qing-Bin Liu and Shi-Zhu He and Cao Liu and Kang Liu and Jun Zhao},
title = {Unsupervised Dialogue State Tracking for End-to-End Task-Oriented Dialogue with a Multi-Span Prediction Network},
year = {2023},
journal = {Journal of Computer Science and Technology},
volume = {38},
number = {4},
pages = {834-852},
keywords = {end-to-end task-oriented dialogue, dialogue state tracking (DST), unsupervised learning, reinforcement learning},
url = {https://www.sciopen.com/article/10.1007/s11390-021-1064-y},
doi = {10.1007/s11390-021-1064-y},
abstract = {This paper focuses on end-to-end task-oriented dialogue systems, which jointly handle dialogue state tracking (DST) and response generation. Traditional methods usually adopt a supervised paradigm to learn DST from a manually labeled corpus. However, the annotation of the corpus is costly, time-consuming, and cannot cover a wide range of domains in the real world. To solve this problem, we propose a multi-span prediction network (MSPN) that performs unsupervised DST for end-to-end task-oriented dialogue. Specifically, MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as keywords. Based on these keywords, MSPN uses a semantic distance based clustering approach to obtain the values of each slot. In addition, we propose an ontology-based reinforcement learning approach, which employs the values of each slot to train MSPN to generate relevant values. Experimental results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant improvements. Besides, we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain, which further demonstrates the adaptability of MSPN.}
}