Linking Entities Across Images and Text
Author
Summary, in English
This paper describes a set of methods to link entities across images and text. As a 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 im- age 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.
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 im- age 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.
Department/s
Publishing year
2015
Language
English
Pages
185-193
Publication/Series
Proceedings of the Nineteenth Conference on Computational Natural Language Learning (CoNLL 2015)
Full text
- Available as PDF - 220 kB
- Download statistics
Links
Document type
Conference paper
Publisher
Association for Computational Linguistics
Topic
- Computer and Information Science
Conference name
Nineteenth Conference on Computational Natural Language Learning (CoNLL 2015)
Conference date
2015-07-30 - 2015-07-31
Conference place
Bejing, China
Status
Published
ISBN/ISSN/Other
- ISBN: 978-1-941643-77-8