Linking Entities Across Images and Text

Weegar, RebeckaStockholms universitet,Institutionen för data- och systemvetenskap (författare)

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.

Åström, Kalle (författare)
Nugues, PierreLund University,Lunds universitet,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH(Swepub:lu)cs-pnu (författare)
Åström, KarlLund 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(Swepub:lu)math-kas (författare)
Stockholms universitetInstitutionen för data- och systemvetenskap (creator_code:org_t)

Ingår i:Proceedings of the 19th Conference on Computational Language LearningStroudsburg, PA, USA : Association for Computational Linguistics, s. 185-1939781941643778

Av författaren/redakt...: Weegar, Rebecka; Åström, Kalle; Nugues, Pierre; Åström, Karl

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Systemvetenskap ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.