Persona-Coded Poly-Encoder: Persona-Guided Multi-Stream Conversational Sentence Scoring

TL;DR

This paper introduces a novel Persona-Coded Poly-Encoder that leverages persona information in multi-stream encoding to enhance response quality in conversational AI, demonstrating improvements over existing methods and enabling better multi-modal data utilization.

Contribution

The paper proposes a new multi-stream encoding approach that effectively incorporates persona data into conversational AI, advancing personalized response generation.

Findings

Improves BLEU score by 3.32% over baseline

Enhances HR@1 by 2.94% compared to state-of-the-art

Facilitates better utilization of multi-modal auxiliary data

Abstract

Recent advances in machine learning and deep learning have led to the widespread use of Conversational AI in many practical applications. However, it is still very challenging to leverage auxiliary information that can provide conversational context or personalized tuning to improve the quality of conversations. For example, there has only been limited research on using an individuals persona information to improve conversation quality, and even state-of-the-art conversational AI techniques are unable to effectively leverage signals from heterogeneous sources of auxiliary data, such as multi-modal interaction data, demographics, SDOH data, etc. In this paper, we present a novel Persona-Coded Poly-Encoder method that leverages persona information in a multi-stream encoding scheme to improve the quality of response generation for conversations. To show the efficacy of the proposed method, we evaluate our method on two different persona-based conversational datasets, and compared against two state-of-the-art methods. Our experimental results and analysis demonstrate that our method can improve conversation quality over the baseline method Poly-Encoder by 3.32% and 2.94% in terms of BLEU score and HR@1, respectively. More significantly, our method offers a path to better utilization of multi-modal data in conversational tasks. Lastly, our study outlines several challenges and future research directions for advancing personalized conversational AI technology.