View on GitHub

KGQA-leaderboard

Repository to track the progress in Question Answering over Knowledge Graphs (KGQA), including the datasets and the current state-of-the-art for the most common KGQA tasks.

TKGQA

TKGQA[1] consists of over 5000 financial news articles regarding the M&A. Each document is paired with extracted tuples (human-extracted and model-predicted) and relevant questions and answers. There are also two temporal knowledge graphs for each document; capturing the state of the temporal knowledge graph before and after the latest facts (extracted tuples)

This dataset can be downloaded via the link.

Reference

[1] Ong, R.; Sun, J.; Șerban, O.; Guo, Y.-K. TKGQA Dataset: Using Question Answering to Guide and Validate the Evolution of Temporal Knowledge Graph. Data 2023, 8, 61.

Go back to README