Personalization in Goal-Oriented Dialog
This work addresses the problem of creating more adaptive and personalized conversational agents for users in goal-oriented scenarios, representing an incremental advance in dialog system research.
The paper tackled the lack of personalization in end-to-end neural dialog systems by introducing a new dataset of goal-oriented dialogs with speaker profiles and proposing architectural modifications to a Memory Network-based system, showing that a single multi-task model outperforms separate profile-specific models.
The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios. End-to-end trained neural dialog systems are an important line of research for such generalized dialog models as they do not resort to any situation-specific handcrafting of rules. However, incorporating personalization into such systems is a largely unexplored topic as there are no existing corpora to facilitate such work. In this paper, we present a new dataset of goal-oriented dialogs which are influenced by speaker profiles attached to them. We analyze the shortcomings of an existing end-to-end dialog system based on Memory Networks and propose modifications to the architecture which enable personalization. We also 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.