Context information modeling is an important task in conversational KBQA. However, existing methods usually assume the independence of utterances and model them in isolation. In this paper, we propose a History Semantic Graph Enhanced KBQA model (HSGE) that is able to effectively model long-range semantic dependencies in conversation history while maintaining low computational cost. The framework incorporates a context-aware encoder, which employs a dynamic memory decay mechanism and models context at different levels of granularity. We evaluate HSGE on a widely used benchmark dataset for complex sequential question answering. Experimental results demonstrate that it outperforms existing baselines averaged on all question types.
@article{arxiv.2306.06872,
title = {History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling},
author = {Hao Sun and Yang Li and Liwei Deng and Bowen Li and Binyuan Hui and Binhua Li and Yunshi Lan and Yan Zhang and Yongbin Li},
journal= {arXiv preprint arXiv:2306.06872},
year = {2023}
}