Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs
This addresses the challenge of answering factual questions with temporal intent over knowledge graphs, which is important for applications like information retrieval and AI assistants, but it appears incremental as it builds on existing KGQA methods by adding a semantic framework.
The paper tackles the problem of generating temporal queries for question answering over knowledge graphs by proposing a semantic framework (SF-TCons) to interpret temporal constraints, and the method SF-TQA significantly outperforms existing methods on two benchmarks.
Answering factual questions with temporal intent over knowledge graphs (temporal KGQA) attracts rising attention in recent years. In the generation of temporal queries, existing KGQA methods ignore the fact that some intrinsic connections between events can make them temporally related, which may limit their capability. We systematically analyze the possible interpretation of temporal constraints and conclude the interpretation structures as the Semantic Framework of Temporal Constraints, SF-TCons. Based on the semantic framework, we propose a temporal question answering method, SF-TQA, which generates query graphs by exploring the relevant facts of mentioned entities, where the exploring process is restricted by SF-TCons. Our evaluations show that SF-TQA significantly outperforms existing methods on two benchmarks over different knowledge graphs.