From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions
Transactions of the association for computational linguistics, 2014•direct.mit.edu
We propose to use the visual denotations of linguistic expressions (ie the set of images they
describe) to define novel denotational similarity metrics, 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 denotation graph, ie a subsumption
hierarchy over constituents and their denotations, based on a large corpus of 30K images
and 150K descriptive captions.
describe) to define novel denotational similarity metrics, 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 denotation graph, ie a subsumption
hierarchy over constituents and their denotations, based on a large corpus of 30K images
and 150K descriptive captions.
Abstract
We propose to use the visual denotations of linguistic expressions (i.e. the set of images they describe) to define novel denotational similarity metrics, 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 denotation graph, i.e. a subsumption hierarchy over constituents and their denotations, based on a large corpus of 30K images and 150K descriptive captions.
MIT Press