When a natural language generation (NLG) component is implemented in a real-world task-oriented dialogue system, it is necessary to generate not only natural utterances as learned on training data but also utterances adapted to the dialogue environment (e.g., noise from environmental sounds) and the user (e.g., users with low levels of understanding ability). Inspired by recent advances in reinforcement learning (RL) for language generation tasks, we propose ANTOR, a method for Adaptive Natural language generation for Task-Oriented dialogue via Reinforcement learning. In ANTOR, a natural language understanding (NLU) module, which corresponds to the user's understanding of system utterances, is incorporated into the objective function of RL. If the NLG's intentions are correctly conveyed to the NLU, which understands a system's utterances, the NLG is given a positive reward. We conducted experiments on the MultiWOZ dataset, and we confirmed that ANTOR could generate adaptive utterances against speech recognition errors and the different vocabulary levels of users.
翻译:当自然语言生成部分(NLG)在现实世界面向任务的对话系统中实施时,不仅需要产生自然语言,了解培训数据,而且需要产生适应对话环境的自然语言(例如,来自环境声音的噪音)和用户(例如,理解能力低的用户)的自然语言生成部分。受最近语言生成任务强化学习(RL)进展的启发,我们建议ANTOR,这是通过强化学习进行面向任务的对话的适应性自然语言生成方法。在ANTOR中,自然语言理解模块(NLU)与用户对系统表达的理解相对应,被纳入RLL的客观功能。如果NLG的意图被正确地传达给了解系统表达的NLU,NLG将得到积极的奖励。我们在多WOZ数据集上进行了实验,我们确认ANTOR可以产生适应性语言识别错误和用户不同词汇水平的表达。