To the top

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

Tell a friend about this page
Print version

Time-Out: Temporal Refere… - University of Gothenburg, Sweden Till startsida
Sitemap
To content Read more about how we use cookies on gu.se

Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change

Conference paper
Authors Haim Dubossarsky
Simon Hengchen
Nina Tahmasebi
Dominik Schlechtweg
Published in Computational linguistics - Association for Computational Linguistics
ISSN 0891-2017
Publication year 2019
Published at Department of Literature, History of Ideas, and Religion
Department of Swedish
Language en
Links https://arxiv.org/abs/1906.01688
Keywords Lexical semantic change, evaluation, data science
Subject categories Language Technology (Computational Linguistics), Information technology

Abstract

State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise. We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset. We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.

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?