arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.04835cs.CLcs.LG
收藏

面向管道目标的对话系统的联合系统级优化

Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System

Tsinghua University(清华大学);JD AI Research(京东人工智能研究院);Stanford University(斯坦福大学)

Zichuan Lin, Jing Huang, Bowen Zhou, Xiaodong He, Tengyu Ma

摘要:

最近的工作(Takanobu等人,2020)提出了对对话系统的系统级评估并发现对单个组件的改进(例如,NLU,政策)在先前的工作可能不一定会带来好处的管道系统在系统明智的评估。为了提高系统性能,在本文中,我们提出了新的联合系统优化技术的管道对话系统。首先,我们提出了一种新的数据增强方法,它可以自动化NLU训练的标记过程。其次,我们提出了一种新的随机政策参数化泊松分布,使更好的探索,并提供了一个原则性的方法来计算策略梯度。第三,我们提出奖励奖金,以帮助政策探索成功的对话。我们的方法优于Takanobu等人(2020)的竞争性管道系统,在标准多域基准数据集MultiWOZ 2.1上,自动系统评估成功率为12%,人工评估成功率为16%,并且还优于DSTC 9最近最先进的端到端训练模型。

英文摘要:

Recent work (Takanobu et al., 2020) proposed the system-wise evaluation on dialog systems and found that improvement on individual components (e.g., NLU, policy) in prior work may not necessarily bring benefit to pipeline systems in system-wise evaluation. To improve the system-wise performance, in this paper, we propose new joint system-wise optimization techniques for the pipeline dialog system. First, we propose a new data augmentation approach which automates the labeling process for NLU training. Second, we propose a novel stochastic policy parameterization with Poisson distribution that enables better exploration and offers a principled way to compute policy gradient. Third, we propose a reward bonus to help policy explore successful dialogs. Our approaches outperform the competitive pipeline systems from Takanobu et al. (2020) by big margins of 12% success rate in automatic system-wise evaluation and of 16% success rate in human evaluation on the standard multi-domain benchmark dataset MultiWOZ 2.1, and also outperform the recent state-of-the-art end-to-end trained model from DSTC9.

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。

↑