GREASE is able to search for the most relevant entities to a query entity provided by a user. It leverages user-provided examples to learn the user-defined relevance. The tool is open-source under the Apache License. [Download]
We provide 10 groups of queries (D1-D10) we created for our experiments. In each file, among every three lines, the first line gives a query entity, the second line gives a list of query-answer pairs as examples, and the third line gives gold-standard answers associated with relevance scores in the form of answer:score. [Download]
How to cite: Tianshuo Zhou, Ziyang Li, Gong Cheng, Jun Wang, Yu’Ang Wei. GREASE: A Generative Model for Relevance Search over Knowledge Graphs. In: WSDM 2020.
Contact Tianshuo Zhou and Gong Cheng with any questions or comments.