Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

Anonymous

Abstract: Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which have raised much attention in recent years. Existing personalized dialogue systems have tried to extract user profiles from dialogue history to guide personalized response generation. Since the dialogue history is usually long and noisy, most existing methods truncate the dialogue history to model the user personality. Such methods can generate some personalized responses, but a large part of dialogue history is wasted, leading to sub-optimal performance of personalized response generation. In this work, we propose to refine the user dialogue history from a large scale, based on which we can handle more dialogue history and obtain a more abundant and accurate persona information. Specifically, we design an MSP model which consists of three personal information refiners and a personalized response generator. With these multi-level refiners, we can sparsely extract the most valuable information (tokens) from the dialogue history and leverage other similar users' data to enhance the personalization. Experimental results on two real-world datasets demonstrate the superiority of our model in generating more informative and personalized responses.

Paper Type: long