论文标题
通过强化学习，适用于任务对话的自适应自然语言生成
Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning
论文作者
论文摘要
当在现实世界中以任务为导向的对话系统中实现自然语言（NLG）组件时，不仅需要在训练数据上学习的自然话语，而且还要生成适合对话环境（例如，来自环境声音的噪音）和用户（例如，使用较低的理解能力的用户）的话语。受到语言生成任务的强化学习（RL）的最新进展的启发，我们提出了Antor，这是一种通过加强学习的自适应自然语言生成的方法。在Antor中，与用户对系统话语的理解相对应的自然语言理解（NLU）模块已纳入RL的目标函数中。如果将NLG的意图正确传达给了NLU，该意图理解了系统的话语，则将给予NLG一个积极的回报。我们在Multiwoz数据集上进行了实验，并确认Antor可以对语音识别错误和用户的不同词汇水平产生适应性话语。
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.
