Negative sampling improves hypernymy extraction based on projection learning

Ustalov, Dmitry ; Arefyev, Nikolay ; Biemann, Chris ; Panchenko, Alexander

Vorschau

PDF
E17-2087.pdf - Veröffentlichte Version
Download (197kB)

URL:	https://ub-madoc.bib.uni-mannheim.de/43325
Weitere URL:	http://aclweb.org/anthology/E17-2
URN:	urn:nbn:de:bsz:180-madoc-433256
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2017
Buchtitel:	15th Conference of the European Chapter of the Association for Computational Linguistics : proceedings of conference : April 3-7, 2017, Valencia, Spain : EACL 2017 ; Vol. 2 : Short papers
Seitenbereich:	543-550
Veranstaltungstitel:	15th Conference of the European Chapter of the Association for Computational Linguistics
Veranstaltungsort:	Valencia, Spain
Veranstaltungsdatum:	April 3-7, 2017
Herausgeber:	Lapata, Mirella
Ort der Veröffentlichung:	Stroudsburg, PA
Verlag:	Association for Computational Linguistics
ISBN:	978-1-945626-35-7
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Fachgebiet:	004 Informatik
Abstract:	We present a new approach to extraction of hypernyms based on projection learning and word embeddings. In contrast to classification-based approaches, projection-based methods require no candidate hyponym-hypernym pairs. While it is natural to use both positive and negative training examples in supervised relation extraction, the impact of positive examples on hypernym prediction was not studied so far. In this paper, we show that explicit negative examples used for regularization of the model significantly improve performance compared to the state-of-the-art approach of Fu et al. (2014) on three datasets from different languages.