To the top

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

Tell a friend about this page
Print version

Exploring the Functional … - University of Gothenburg, Sweden Till startsida
Sitemap
To content Read more about how we use cookies on gu.se

Contact form








 


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




Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models

Conference paper
Authors Simon Dobnik
Mehdi Ghanimifard
John D. Kelleher
Published in Proceedings of SpLU 2018 at NAACL-HLT 2018, June 6, 2018 New Orleans, Louisiana / Parisa Kordjamshidi, Archna Bhatia, James Pustejovsky, Marie-Francine Moens (eds.)
ISBN 978-1-948087-21-6
Publisher Association of Computational Linguistics (ACL)
Place of publication New Orleans, Louisiana, USA
Publication year 2018
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Links aclweb.org/anthology/W18-14
https://gup.ub.gu.se/file/207403
Keywords spatial descriptions, grounding, semantics, semantic representations, neural language model, machine learning, deep neural networks, image captioning
Subject categories Computational linguistics, Linguistics, Cognitive science

Abstract

The challenge for computational models of spatial descriptions for situated dialogue systems is the integration of information from different modalities. The semantics of spatial descriptions are grounded in at least two sources of information: (i) a geometric representation of space and (ii) the functional interaction of related objects that. We train several neural language models on descriptions of scenes from a dataset of image captions and examine whether the functional or geometric bias of spatial descriptions reported in the literature is reflected in the estimated perplexity of these models. The results of these experiments have implications for the creation of models of spatial lexical semantics for human-robot dialogue systems. Furthermore, they also provide an insight into the kinds of the semantic knowledge captured by neural language models trained on spatial descriptions, which has implications for image captioning systems.

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?