Effortless Integration of Memory Management into Open-Domain Conversation Systems

TL;DR

This paper introduces a simple, low-cost method to enhance open-domain conversation systems by integrating memory management, leading to improved performance without affecting other tasks.

Contribution

The paper presents BlenderBot3-M^3, a novel multi-task training approach that incorporates memory management into BlenderBot3 with minimal data creation effort.

Findings

BlenderBot3-M^3 outperforms BlenderBot3 with a 4% F1 score increase.

The proposed method reduces external memory usage.

Memory management integration does not impair other task performances.

Abstract

Open-domain conversation systems integrate multiple conversation skills into a single system through a modular approach. One of the limitations of the system, however, is the absence of management capability for external memory. In this paper, we propose a simple method to improve BlenderBot3 by integrating memory management ability into it. Since no training data exists for this purpose, we propose an automating dataset creation for memory management. Our method 1) requires little cost for data construction, 2) does not affect performance in other tasks, and 3) reduces external memory. We show that our proposed model BlenderBot3-M^3, which is multi-task trained with memory management, outperforms BlenderBot3 with a relative 4% performance gain in terms of F1 score.