arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.11904cs.CLcs.AI
收藏

可转移的对话系统和用户模拟器

Transferable Dialogue Systems and User Simulators

University of Cambridge(剑桥大学);Alibaba Group(阿里巴巴集团)

Bo-Hsiang Tseng, Yinpei Dai, Florian Kreyssig, Bill Byrne

摘要:

训练对话系统的困难之一是缺乏训练数据。我们探讨了通过对话系统和用户模拟器之间的交互来创建对话数据的可能性。我们的目标是开发一个建模框架,可以通过两个代理之间的自我发挥,将新的对话场景。在这个框架中,我们首先在源域对话的集合上对两个代理进行预训练,这使得代理能够通过自然语言相互交谈。通过对少量目标域数据的进一步微调,代理继续进行交互,目的是使用具有结构化奖励函数的强化学习来改善其行为。在MultiWOZ数据集上的实验中,研究了两个实际的迁移学习问题:1)领域自适应和2)单域到多域迁移。我们证明了所提出的框架是非常有效的引导性能的两个代理迁移学习。我们还表明,我们的方法导致对话系统性能的改善,在完整的数据集。

英文摘要:

One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue system and a user simulator. Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents. In this framework, we first pre-train the two agents on a collection of source domain dialogues, which equips the agents to converse with each other via natural language. With further fine-tuning on a small amount of target domain data, the agents continue to interact with the aim of improving their behaviors using reinforcement learning with structured reward functions. In experiments on the MultiWOZ dataset, two practical transfer learning problems are investigated: 1) domain adaptation and 2) single-to-multiple domain transfer. We demonstrate that the proposed framework is highly effective in bootstrapping the performance of the two agents in transfer learning. We also show that our method leads to improvements in dialogue system performance on complete datasets.

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。

↑