arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.03274cs.AIcs.CL
收藏

Hybrid Code Networks:通过监督和强化学习实现实用高效的端到端对话控制

Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

Microsoft Research(微软研究院);Brown University(布朗大学);JPMorgan Chase(摩根大通)

Jason D. Williams, Kavosh Asadi, Geoffrey Zweig

摘要:

递归神经网络(RNN)的端到端学习是对话系统的一个有吸引力的解决方案;然而,目前的技术是数据密集型的,需要数千个对话框来学习简单的行为。我们介绍了混合代码网络(HCN),它将RNN与编码为软件和系统动作模板的特定领域知识相结合。与现有的端到端方法相比,HCN大大减少了所需的训练数据量,同时保留了推断对话状态的潜在表示的关键优势。此外,HCN可以用监督学习、强化学习或两者的混合来优化。HCN在bAbI对话数据集上获得了最先进的性能,并且优于两个商业部署的面向客户的对话系统。

英文摘要:

End-to-end learning of recurrent neural networks (RNNs) is an attractive solution for dialog systems; however, current techniques are data-intensive and require thousands of dialogs to learn simple behaviors. We introduce Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates. Compared to existing end-to-end approaches, HCNs considerably reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state. In addition, HCNs can be optimized with supervised learning, reinforcement learning, or a mixture of both. HCNs attain state-of-the-art performance on the bAbI dialog dataset, and outperform two commercially deployed customer-facing dialog systems.

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。

↑