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.
@article{arxiv.2305.13973,
title = {Effortless Integration of Memory Management into Open-Domain Conversation Systems},
author = {Eunbi Choi and Kyoung-Woon On and Gunsoo Han and Sungwoong Kim and Daniel Wontae Nam and Daejin Jo and Seung Eun Rho and Taehwan Kwon and Minjoon Seo},
journal= {arXiv preprint arXiv:2305.13973},
year = {2023}
}