Loading…

From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions

We propose to use the of linguistic expressions (i.e. the set of images they describe) to define novel , which we show to be at least as beneficial as distributional similarities for two tasks that require semantic inference. To compute these denotational similarities, we construct a , i.e. a subsum...

Full description

Saved in:
Bibliographic Details
Published in:Transactions of the Association for Computational Linguistics 2014-12, Vol.2, p.67-78
Main Authors: Young, Peter, Lai, Alice, Hodosh, Micah, Hockenmaier, Julia
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose to use the of linguistic expressions (i.e. the set of images they describe) to define novel , which we show to be at least as beneficial as distributional similarities for two tasks that require semantic inference. To compute these denotational similarities, we construct a , i.e. a subsumption hierarchy over constituents and their denotations, based on a large corpus of 30K images and 150K descriptive captions.
ISSN:2307-387X
2307-387X
DOI:10.1162/tacl_a_00166