To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Training Word Sense Embed… - University of Gothenburg, Sweden Till startsida
Sitemap
To content Read more about how we use cookies on gu.se

Training Word Sense Embeddings With Lexicon-based Regularization

Conference paper
Authors Luis Nieto Piña
Richard Johansson
Published in Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Taipei, Taiwan, November 27 – December 1, 2017
ISBN 978-1-948087-00-1
Publisher Asian Federation of Natural Language Processing
Publication year 2017
Published at Department of Swedish
Department of Computer Science and Engineering (GU)
Language en
Links www.aclweb.org/anthology/I17-1029
Keywords natural language processing, swedish language, lexicon, embedding, neural network, semantics, meaning representation
Subject categories Data processing, Language Technology (Computational Linguistics)

Abstract

We propose to improve word sense embeddings by enriching an automatic corpus-based method with lexicographic data. Information from a lexicon is introduced into the learning algorithm’s objective function through a regularizer. The incorporation of lexicographic data yields embeddings that are able to reflect expertdefined word senses, while retaining the robustness, high quality, and coverage of automatic corpus-based methods. These properties are observed in a manual inspection of the semantic clusters that different degrees of regularizer strength create in the vector space. Moreover, we evaluate the sense embeddings in two downstream applications: word sense disambiguation and semantic frame prediction, where they outperform simpler approaches. Our results show that a corpusbased model balanced with lexicographic data learns better representations and improve their performance in downstream tasks

Page Manager: Webmaster|Last update: 9/11/2012
Share:

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?