Relation extraction on an open-domain knowledge base
Accompanying repository for our EMNLP 2017 paper. It contains the code to replicate the experiments and the pre-trained models for sentence-level relation extraction.
Anything To Triples (any23) is a library, a web service and a command line tool that extracts structured data in RDF format from a variety of Web documents.
To help researchers investigate relation extraction, we’re releasing a human-judged dataset of two relations about public figures on Wikipedia: nearly 10,000 examples of “place of birth”, and over 40,000 examples of “attended or graduated from an institution”. Each of these was judged by at least 5 raters, and can be used to train or evaluate relation extraction systems. We also plan to release more relations of new types in the coming months.
M. Schwab, R. Jäschke, и F. Fischer. Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, стр. 110--115. Association for Computational Linguistics, (2023)
M. Schwab, R. Jäschke, и F. Fischer. Proceedings of the 5th International Conference on Natural Language and Speech Processing, стр. 282--287. Association for Computational Linguistics, (2022)
F. Arnold, и R. Jäschke. Proceedings of the Workshop Understanding LIterature references in academic full TExt at JCDL 2022, том 3220 из ULITE-ws '22, стр. 7--15. CEUR Workshop Proceedings, (2022)