@article{Mo_Zhang_Li_Li_Yang_2018, title={Personalizing a Dialogue System With Transfer Reinforcement Learning}, volume={32}, url={https://ojs.aaai.org/index.php/AAAI/article/view/11938}, DOI={10.1609/aaai.v32i1.11938}, abstractNote={ <p> 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 is likely to 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 as a source domain and an individual user as a target domain, and to perform transfer learning from the source domain to the target domain. By following this idea, we propose a PErsonalized Task-oriented diALogue (PETAL) system, a transfer reinforcement learning framework based on POMDP, to construct a personalized dialogue system. The PETAL system first learns common dialogue knowledge from the source domain and then adapts this knowledge to the target domain. The proposed PETAL system can avoid the negative transfer problem by considering differences between the source and target users in a personalized Q-function. Experimental results on a real-world coffee-shopping data and simulation data show that the proposed PETAL system can learn optimal policies for different users, and thus effectively improve the dialogue quality under the personalized setting. </p> }, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Mo, Kaixiang and Zhang, Yu and Li, Shuangyin and Li, Jiajun and Yang, Qiang}, year={2018}, month={Apr.} }