《Personlization in Goal-oriented Dialog》(Chaitanya K. Joshi,EPFL(洛桑联邦理工学院),2017NIPS)
本篇源码已公开,地址:https://github.com/chaitjo/personalized-dialog/tree/master/MemN2N-split-memory
本论文对bAbI对话数据集进行扩展,提供了一个新的数据集。
Motivation
- Personalization is key to creating conversational agents, and incorporating personalization into end-to-end trained neural dialog systems is a largely unexplored topic.
Contribution
- Present a new dataset of goal-oriented dialogs.
- Propose modifications to the architecture which enable personalization.
- Investigate personalization in dialog as a multi-task learning problem, and show that a single model which shares features among various profiles outperforms separate models for each profile.