Search: onr:"swepub:oai:DiVA.org:su-144927" >
Linking Entities Ac...
Linking Entities Across Images and Text
-
- Weegar, Rebecka (author)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
Åström, Kalle (author)
-
- Nugues, Pierre (author)
- Lund University,Lunds universitet,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH
-
show more...
-
- Åström, Karl (author)
- Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH
-
show less...
-
(creator_code:org_t)
- Stroudsburg, PA, USA : Association for Computational Linguistics, 2015
- 2015
- English.
-
In: Proceedings of the 19th Conference on Computational Language Learning. - Stroudsburg, PA, USA : Association for Computational Linguistics. - 9781941643778 ; , s. 185-193
- Related links:
-
https://doi.org/10.1...
-
show more...
-
https://www.aclweb.o...
-
https://portal.resea... (primary) (free)
-
http://www.aclweb.or... (free)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://lup.lub.lu.s...
-
show less...
Abstract
Subject headings
Close
- This paper describes a set of methods to link entities across images and text. Asa corpus, we used a data set of images, where each image is commented by a short caption and where the regions in the images are manually segmented and labeled with a category. We extracted the entity mentions from the captions and we computed a semantic similarity between the mentions and the region labels. We also measured the statistical associations between these mentions and the labels and we combined them with the semantic similarity to produce mappings in the form of pairs consisting of a region label and a caption entity. In a second step, we used the syntactic relationships between the mentions and the spatial relationships between the regions to rerank the lists of candidate mappings. To evaluate our methods, we annotated a test set of 200 images, where we manually linked the image regions to their corresponding mentions in the captions. Eventually, we could match objects in pictures to their correct mentions for nearly 89 percent of the segments, when such a matching exists.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Systemvetenskap, informationssystem och informatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Information Systems (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Keyword
- data- och systemvetenskap
- Computer and Systems Sciences
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database