Question Answering Over Temporal Knowledge Graphs

TL;DR

This paper introduces CRONQUESTIONS, the largest Temporal KGQA dataset, and proposes CRONKGQA, a transformer-based method that significantly outperforms existing approaches in answering questions over temporal knowledge graphs.

Contribution

The paper presents a large, stratified Temporal KGQA dataset and a novel transformer-based model that achieves state-of-the-art performance, advancing research in temporal question answering.

Findings

CRONQUESTIONS expands previous datasets by 340x.

CRONKGQA improves accuracy by 120% over baselines.

State-of-the-art methods underperform on the new dataset.

Abstract

Temporal Knowledge Graphs (Temporal KGs) extend regular Knowledge Graphs by providing temporal scopes (start and end times) on each edge in the KG. While Question Answering over KG (KGQA) has received some attention from the research community, QA over Temporal KGs (Temporal KGQA) is a relatively unexplored area. Lack of broad coverage datasets has been another factor limiting progress in this area. We address this challenge by presenting CRONQUESTIONS, the largest known Temporal KGQA dataset, clearly stratified into buckets of structural complexity. CRONQUESTIONS expands the only known previous dataset by a factor of 340x. We find that various state-of-the-art KGQA methods fall far short of the desired performance on this new dataset. In response, we also propose CRONKGQA, a transformer-based solution that exploits recent advances in Temporal KG embeddings, and achieves performance superior to all baselines, with an increase of 120% in accuracy over the next best performing method. Through extensive experiments, we give detailed insights into the workings of CRONKGQA, as well as situations where significant further improvements appear possible. In addition to the dataset, we have released our code as well.