One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles

TL;DR

This paper introduces a method for creating personalized chatbots by automatically learning implicit user profiles from dialogue history, enabling more natural and user-specific responses without the need for explicit profile data.

Contribution

The paper proposes a novel approach that automatically constructs dynamic user profiles from dialogue history using Transformer models and key-value memory networks, improving personalization in chatbots.

Findings

Significant performance improvements over existing methods.

Effective dynamic user profiling from large-scale dialogue data.

Enhanced response relevance and personalization.

Abstract

Personalized chatbots focus on endowing chatbots with a consistent personality to behave like real users, give more informative responses, and further act as personal assistants. Existing personalized approaches tried to incorporate several text descriptions as explicit user profiles. However, the acquisition of such explicit profiles is expensive and time-consuming, thus being impractical for large-scale real-world applications. Moreover, the restricted predefined profile neglects the language behavior of a real user and cannot be automatically updated together with the change of user interests. In this paper, we propose to learn implicit user profiles automatically from large-scale user dialogue history for building personalized chatbots. Specifically, leveraging the benefits of Transformer on language understanding, we train a personalized language model to construct a general user profile from the user's historical responses. To highlight the relevant historical responses to the input post, we further establish a key-value memory network of historical post-response pairs, and build a dynamic post-aware user profile. The dynamic profile mainly describes what and how the user has responded to similar posts in history. To explicitly utilize users' frequently used words, we design a personalized decoder to fuse two decoding strategies, including generating a word from the generic vocabulary and copying one word from the user's personalized vocabulary. Experiments on two real-world datasets show the significant improvement of our model compared with existing methods. Our code is available at https://github.com/zhengyima/DHAP