To the top

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

Tell a friend about this page
Print version

"Deep" Learning : Detecti… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

"Deep" Learning : Detecting Metaphoricity in Adjective-Noun Pairs

Conference paper
Authors Yuri Bizzoni
Stergios Chatzikyriakidis
Mehdi Ghanimifard
Published in Proceedings of the Workshop on Stylistic Variation, EMNLP2017, Copenhagen, Denmark, September 7–11, 2017
ISBN 978-1-945626-99-9
Publisher Association for Computational Linguistics (ACL)
Place of publication Copenhagen, Denmark
Publication year 2017
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Subject categories Languages and Literature, Computer and Information Science


Metaphor is one of the most studied and widespread figures of speech and an essential element of individual style. In this paper we look at metaphor identification in Adjective-Noun pairs. We show that using a single neural network combined with pre-trained vector embeddings can outperform the state of the art in terms of accuracy. In specific, the approach presented in this paper is based on two ideas: a) transfer learning via using pre-trained vectors representing adjective noun pairs, and b) a neural network as a model of composition that predicts a metaphoricity score as output. We present several different architectures for our system and evaluate their performances. Variations on dataset size and on the kinds of embeddings are also investigated. We show considerable improvement over the previous approaches both in terms of accuracy and w.r.t the size of annotated training data.

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?