A Corpus-Free State2Seq User Simulator for Task-Oriented Dialogue

• Published in: Chinese Computational Linguistics pp. 689 - 702
• Main Authors: Hou, Yutai, Fang, Meng, Che, Wanxiang, Liu, Ting
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing 2019
• Series: Lecture Notes in Computer Science
• ISBN: 3030323803; 9783030323806
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-32381-3_55

Recent reinforcement learning algorithms for task-oriented dialogue system absorbs a lot of interest. However, an unavoidable obstacle for training such algorithms is that annotated dialogue corpora are often unavailable. One of the popular approaches addressing this is to train a dialogue agent with a user simulator. Traditional user simulators are built upon a set of dialogue rules and therefore lack response diversity. This severely limits the simulated cases for agent training. Later data-driven user models work better in diversity but suffer from data scarcity problem. To remedy this, we design a new corpus-free framework that taking advantage of their benefits. The framework builds a user simulator by first generating diverse dialogue data from templates and then build a new State2Seq user simulator on the data. To enhance the performance, we propose the State2Seq user simulator model to efficiently leverage dialogue state and history. Experiment results on an open dataset show that our user simulator helps agents achieve an improvement of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$6.36\%$$\end{document} on success rate. State2Seq model outperforms the seq2seq baseline for 1.9 F-score.