Personalized Response Generation via Domain adaptation
Personalized Response Generation via Domain adaptation
复制标题
DOI：
10.1145/3077136.3080706
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Min Yang;Zhou Zhao;Wei Zhao;Xiaojun Chen;Jia Zhu;Lianqiang Zhou;Zigang Cao
中科院分区：
文献类型：
--
作者：
Min Yang;Zhou Zhao;Wei Zhao;Xiaojun Chen;Jia Zhu;Lianqiang Zhou;Zigang Cao
本文提出了一种基于领域适应（PRG-DM）的个性化响应生成模型。首先，我们从大量的通用数据（没有用户特定的信息）中学习人类的响应风格。其次，我们在小尺寸的个性化数据上微调模型，通过双重学习机制生成个性化响应。此外，我们提出了三种新的奖励来描述个性化、信息性和语法性好的对话。我们采用策略梯度方法来生成高回报的响应。实验结果表明，该模型可以针对不同用户生成更好的个性化响应。
In this paper, we propose a novel personalized response generation model via domain adaptation (PRG-DM). First, we learn the human responding style from large general data (without user-specific information). Second, we fine tune the model on a small size of personalized data to generate personalized responses with a dual learning mechanism. Moreover, we propose three new rewards to characterize good conversations that are personalized, informative and grammatical. We employ the policy gradient method to generate highly rewarded responses. Experimental results show that our model can generate better personalized responses for different users.