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.- Anthology ID:
- Q14-1006
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 2
- Month:
- Year:
- 2014
- Address:
- Cambridge, MA
- Editors:
- Dekang Lin, Michael Collins, Lillian Lee
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 67–78
- Language:
- URL:
- https://aclanthology.org/Q14-1006
- DOI:
- 10.1162/tacl_a_00166
- Cite (ACL):
- Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. 2014. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics, 2:67–78.
- Cite (Informal):
- From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (Young et al., TACL 2014)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/Q14-1006.pdf
- Data
- Flickr30k