The Hidden Agenda User Simulation Model
The Hidden Agenda User Simulation Model
复制标题
DOI：
10.1109/tasl.2008.2012071
复制
发表时间：
2009-05
期刊：
影响因子：
--
通讯作者：
J. Schatzmann;S. Young
中科院分区：
文献类型：
--
作者：
J. Schatzmann;S. Young
对口语对话系统采用统计方法的一个关键优势是能够将对话策略设计形式化为随机优化问题。然而，由于对话策略是通过交互式探索替代对话路径来学习的，因此传统的静态对话语料库不能直接用于训练，而是通常使用用户模拟器。本文描述了一种新的统计用户模型，该模型基于一种紧凑的类似堆栈的状态表示，称为用户议程，它允许将状态转换建模为推送和弹出操作的序列，并从用户的角度优雅地编码对话历史。提出了一种基于期望最大化的算法，该算法根据隐藏状态序列对可观察到的用户输出进行建模，从而允许模型在最小注释数据的语料库上进行训练。真实世界对话系统的实验结果表明，经过训练的用户模型可以成功地用于优化对话策略，该策略在任务完成率和用户满意度得分方面优于手工制作的基线。
A key advantage of taking a statistical approach to spoken dialogue systems is the ability to formalise dialogue policy design as a stochastic optimization problem. However, since dialogue policies are learnt by interactively exploring alternative dialogue paths, conventional static dialogue corpora cannot be used directly for training and instead, a user simulator is commonly used. This paper describes a novel statistical user model based on a compact stack-like state representation called a user agenda which allows state transitions to be modeled as sequences of push- and pop-operations and elegantly encodes the dialogue history from a user's point of view. An expectation-maximisation based algorithm is presented which models the observable user output in terms of a sequence of hidden states and thereby allows the model to be trained on a corpus of minimally annotated data. Experimental results with a real-world dialogue system demonstrate that the trained user model can be successfully used to optimise a dialogue policy which outperforms a hand-crafted baseline in terms of task completion rates and user satisfaction scores.