History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
This work addresses the challenge of context information modeling in conversational KBQA, which is incremental as it builds on existing methods by enhancing semantic dependency handling while maintaining computational efficiency.
The paper tackles the problem of modeling long-range semantic dependencies in conversational knowledge base question answering (KBQA) by proposing a History Semantic Graph Enhanced model (HSGE) that incorporates a context-aware encoder with dynamic memory decay and multi-granularity context modeling, achieving improved performance over existing baselines on a benchmark dataset.
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.