To the top

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

Tell a friend about this page
Print version

Language Modeling with Sy… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Contact form


Note! If you want an answer on a question you must specify your email address

Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions

Conference paper
Authors Adam Ek
Jean-Philippe Bernardy
Shalom Lappin
Published in Proceedings of the 22nd Nordic Conference on Computational Linguistics, 30 September – 2 October, 2019, Turku, Finland / Mareike Hartmann, Barbara Plank (Editors)
ISBN 978-91-7929-995-8
ISSN 1650-3686
Publisher Linköping University Electronic Press
Place of publication University of Linköping
Publication year 2019
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Keywords deep learning and syntax, deep learning and semantics, computational model of sentence acceptability
Subject categories Computational linguistics, Computer Science


In this paper, we investigate the effect of enhancing lexical embeddings in LSTM language models (LM) with syntactic and semantic representations. We evaluate the language models using perplexity, and we evaluate the performance of the models on the task of predicting human sentence acceptability judgments. We train LSTM language models on sentences automatically annotated with universal syntactic dependency roles (Nivre, 2016), dependency depth and universal semantic tags (Abzianidze et al., 2017) to predict sentence acceptability judgments. Our experiments indicate that syntactic tags lower perplexity, while semantic tags increase it. Our experiments also show that neither syntactic nor semantic tags improve the performance of LSTM language models on the task of predicting sentence acceptability judgments.

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

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?

Denna text är utskriven från följande webbsida:
Utskriftsdatum: 2020-05-28