arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07263cs.CLcs.LG
收藏

基于流程图的面向任务对话的端到端学习

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

Indian Institute of Technology, New Delhi(印度理工学院新德里分校);IBM Research, New Delhi(IBM研究院新德里)

Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi, Mausam

摘要:

我们在面向任务的对话(TOD)的端到端学习中提出了一个新问题,其中对话系统模仿通过诊断用户的问题来帮助用户的故障排除代理(例如,汽车不能启动)。这样的对话基于特定领域的流程图,代理应该在对话期间遵循这些流程图。我们的任务暴露了神经TOD的新技术挑战,例如将话语接地到没有明确注释的流程图,当用户问澄清问题时参考额外的手册页面,以及在测试时遵循看不见的流程图的能力。我们发布了一个数据集(FloDial),由2,738个基于12个不同故障排除流程图的对话框组成。我们还设计了一个神经模型,FloNet,它使用检索增强生成架构训练对话代理。我们的实验发现,FloNet可以对看不见的流程图进行zero-shot传输,并为未来的研究奠定了坚实的基础。

英文摘要:

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FloDial) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FloNet, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FloNet can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.

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。

↑