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

TL;DR

This paper introduces a novel method for refining dialogue history in personalized dialogue systems, enabling the use of more relevant information for generating more accurate and personalized responses.

Contribution

It proposes the MSP model with multi-level personal information refiners to better extract valuable user data from long dialogue histories.

Findings

Outperforms existing models in generating personalized responses

Utilizes similar users' data to enhance personalization

Demonstrates effectiveness on real-world datasets

Abstract

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which has 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's 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 on a large scale, based on which we can handle more dialogue history and obtain 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 personalization. Experimental results on two real-world datasets demonstrate the superiority of our model in generating more informative and personalized responses.