End-to-end Relation Extraction using distant supervision from external semantic repositories
|End-to-end Relation Extraction using distant supervision from external semantic repositories|
|Author(s)||Nguyen T.-V.T., Moschitti A.|
|Published in||ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies|
|Keyword(s)||Unknown (Extra: Named entities, Relation extraction, Semantic repository, Test sets, Text document, Training data, Wikipedia, Computational linguistics, Semantics, Websites, Experiments)|
|Article||BASE, CiteSeerX, Google Scholar|
|Web||Ask, Bing, Google (PDF), Yahoo!|
|Download and mirrors|
|Local copy||Not available|
|Remote mirror(s)||Not available|
|Export and share|
|BibTeX, CSV, RDF, JSON|
|Browse properties · List of conference papers|
End-to-end Relation Extraction using distant supervision from external semantic repositories is a 2011 conference paper written in English by Nguyen T.-V.T., Moschitti A. and published in ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies.
In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entities in target relations is enough to produce reliable supervision. Our experiments with state-of-the-art relation extraction models, trained on the above data, show a meaningful F1 of 74.29% on a manually annotated test set: this highly improves the state-of-art in RE using DS. Additionally, our end-to-end experiments demonstrated that our extractors can be applied to any general text document.
- This section requires expansion. Please, help!
Probably, this publication is cited by others, but there are no articles available for them in WikiPapers. Cited 13 time(s)