Negative sampling improves hypernymy extraction based on projection learning

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

E17-2087.pdf - Published

Download (197kB)

Additional URL:
URN: urn:nbn:de:bsz:180-madoc-433256
Document Type: Conference or workshop publication
Year of publication: 2017
Book title: 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
Page range: 543-550
Conference title: 15th Conference of the European Chapter of the Association for Computational Linguistics
Location of the conference venue: Valencia, Spain
Date of the conference: April 3-7, 2017
Publisher: Lapata, Mirella
Place of publication: Stroudsburg, PA
Publishing house: Association for Computational Linguistics
ISBN: 978-1-945626-35-7
Publication language: English
Institution: School of Business Informatics and Mathematics > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Subject: 004 Computer science, internet
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.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item