Personalization in Goal-Oriented Dialog

TL;DR

This paper introduces a new dataset and architectural modifications for goal-oriented dialog systems to incorporate personalization, demonstrating that shared models outperform profile-specific ones in multi-task learning settings.

Contribution

The paper presents a novel dataset of personalized goal-oriented dialogs and proposes architectural and training modifications to enable personalization in neural dialog systems.

Findings

Shared models outperform separate models for each profile.

Architectural modifications enable effective personalization.

New dataset facilitates research on personalized dialog systems.

Abstract

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.