To the top

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

Tell a friend about this page
Print version

Modular Mechanistic Netwo… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Modular Mechanistic Networks for Computational Modelling of Spatial Descriptions

Conference contribution
Authors Simon Dobnik
John D. Kelleher
Published in Abstracts of the Seventh Swedish Language Technology Conference (SLTC-2018), 7-9 November 2018, Stockholm
Place of publication Stockholm, Sweden
Publication year 2018
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Keywords spatial descriptions deep learning neural networks modular architectures language and vision image captioning
Subject categories Computational linguistics


We argue current deep learning approaches to modelling of spatial language in generating image captions have shortcomings and that the multiplicity of factors that influence spatial language invites a modular approach where the solution can be built in a piece-wise manner and then integrated. We call this approach where deep learning is assisted with domain knowledge expressed as modules that are trained on data a top-down or mechanistic approach to otherwise a bottom-up phenomenological approach.

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?