Complex Temporal Question Answering on Knowledge Graphs

TL;DR

This paper introduces EXAQT, an end-to-end system for answering complex temporal questions over knowledge graphs, combining subgraph extraction, temporal fact enhancement, and graph neural networks to improve accuracy.

Contribution

The work presents the first comprehensive system for complex temporal KG-QA, integrating subgraph extraction, temporal fact augmentation, and R-GCNs with temporal embeddings.

Findings

EXAQT outperforms three state-of-the-art systems on the TimeQuestions dataset.

The system effectively combines high recall subgraph extraction with precision-focused ranking.

Temporal fact augmentation improves the relevance of answer retrieval.

Abstract

Question answering over knowledge graphs (KG-QA) is a vital topic in IR. Questions with temporal intent are a special class of practical importance, but have not received much attention in research. This work presents EXAQT, the first end-to-end system for answering complex temporal questions that have multiple entities and predicates, and associated temporal conditions. EXAQT answers natural language questions over KGs in two stages, one geared towards high recall, the other towards precision at top ranks. The first step computes question-relevant compact subgraphs within the KG, and judiciously enhances them with pertinent temporal facts, using Group Steiner Trees and fine-tuned BERT models. The second step constructs relational graph convolutional networks (R-GCNs) from the first step's output, and enhances the R-GCNs with time-aware entity embeddings and attention over temporal relations. We evaluate EXAQT on TimeQuestions, a large dataset of 16k temporal questions we compiled from a variety of general purpose KG-QA benchmarks. Results show that EXAQT outperforms three state-of-the-art systems for answering complex questions over KGs, thereby justifying specialized treatment of temporal QA.