Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs

TL;DR

This paper introduces SF-TQA, a novel method for temporal question answering over knowledge graphs that leverages a semantic framework of temporal constraints, significantly improving performance over existing approaches.

Contribution

The paper proposes SF-TCons, a semantic framework for interpreting temporal constraints, and develops SF-TQA, a method that generates query graphs based on this framework for better temporal KGQA.

Findings

SF-TQA outperforms existing methods on benchmark datasets.

The semantic framework effectively captures intrinsic event connections.

Exploring relevant facts within SF-TCons improves query generation accuracy.

Abstract

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.