arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04686cs.CLcs.AI
收藏

基于强化学习的不确定规划自然语言生成

Natural Language Generation as Planning under Uncertainty Using Reinforcement Learning

School of Informatics(信息学院);University of Edinburgh(爱丁堡大学)

Verena Rieser, Oliver Lemon

摘要:

我们提出并评估了一个新的模型,自然语言生成(NLG)在口语对话系统,统计规划的基础上,从当前生成的上下文(例如,用户和表面实现)的嘈杂的反馈。我们研究了它在一个标准的NLG问题中的使用:如何向用户呈现信息(在这种情况下是一组搜索结果),考虑到话语长度,传达的信息量和认知负荷之间的复杂权衡。我们通过分析现有的MATCH数据来设置这些权衡。然后,我们使用强化学习(RL)训练NLG策略,该策略使其行为适应来自当前生成上下文的噪声反馈。将这一政策与这一领域以往工作中的几条基线进行了比较。学习策略的性能明显优于所有先前的方法。

英文摘要:

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its use in a standard NLG problem: how to present information (in this case a set of search results) to users, given the complex trade- offs between utterance length, amount of information conveyed, and cognitive load. We set these trade-offs by analysing existing MATCH data. We then train a NLG pol- icy using Reinforcement Learning (RL), which adapts its behaviour to noisy feed- back from the current generation context. This policy is compared to several base- lines derived from previous work in this area. The learned policy significantly out- performs all the prior approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑