Personalizing a Dialogue System with Transfer Learning
Personalizing a Dialogue System with Transfer Learning
复制标题
DOI：
--
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Kaixiang Mo;Shuangyin Li;Yu Zhang;Jiajun Li;Qiang Yang
中科院分区：
文献类型：
--
作者：
Kaixiang Mo;Shuangyin Li;Yu Zhang;Jiajun Li;Qiang Yang
训练一个个性化的面向任务的对话系统是很困难的，因为从每个人身上收集到的数据往往是不够的。在小数据集上训练的个性化对话系统可能会过度拟合，使其难以适应不同的用户需求。解决这个问题的一种方法是将多个用户的数据集合作为源域，将单个用户的数据作为目标域，并执行从源域到目标域的迁移学习。在此基础上，我们提出了基于POMDP的迁移学习框架“PETAL”（PErsonalized Task-oriented diALogue，个性化任务导向对话）来学习个性化对话系统。系统首先从源域学习常见的对话知识，然后将这些知识应用于目标用户。该框架通过考虑源用户和目标用户之间的差异，避免了负迁移问题。个性化POMDP中的策略可以学习为不同的用户适当地选择不同的操作。在真实的咖啡购物数据和仿真数据上的实验结果表明，我们的个性化对话系统可以针对不同的用户选择不同的最优动作，从而有效地提高个性化设置下的对话质量。
It is difficult to train a personalized task-oriented dialogue system because the data collected from each individual is often insufficient. Personalized dialogue systems trained on a small dataset can overfit and make it difficult to adapt to different user needs. One way to solve this problem is to consider a collection of multiple users’ data as a source domain and an individual user’s data as a target domain, and to perform a transfer learning from the source to the target domain. By following this idea, we propose the “PETAL” (PErsonalized Task-oriented diALogue), a transfer learning framework based on POMDP to learn a personalized dialogue system. The system first learns common dialogue knowledge from the source domain and then adapts this knowledge to the target user. This framework can avoid the negative transfer problem by considering differences between source and target users. The policy in the personalized POMDP can learn to choose different actions appropriately for different users. Experimental results on a real-world coffee-shopping data and simulation data show that our personalized dialogue system can choose different optimal actions for different users, and thus effectively improve the dialogue quality under the personalized setting.