To the top

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

Tell a friend about this page
Print version

Predicting Metaphor Parap… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Predicting Metaphor Paraphrase Judgements in Context

Conference paper
Authors Yuri Bizzoni
Shalom Lappin
Published in Proceedings of the 13th International Conference on Computational Semantics 2019 - Long Papers, 23–27 May 2019, Gothenburg, Sweden / Simon Dobnik, Stergios Chatzikyriakidis, Vera Demberg (Editors)
ISBN 978-1-950737-19-2
Publisher Association of Computational Linguistics
Place of publication Stroudsburg, PA
Publication year 2019
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Keywords metaphor in context computational modelling deep learning paraphrase prediction
Subject categories Computational linguistics, Information technology


We conduct two experiments to study the effect of context on metaphor paraphrase aptness judg- ments. The first is an AMT crowd source task in which speakers rank metaphor-paraphrase candidate sentence pairs in short document contexts for paraphrase aptness. In the second we train a composite DNN to predict these human judgments, first in binary classifier mode, and then as gradient ratings. We found that for both mean human judgments and our DNN modeling, adding document context compresses the aptness scores towards the centre of the scale, raising low out of context ratings and decreasing high out of context scores. We briefly consider two possible explanations for this compression effect.

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?