Visual Entity Linking: A Preliminary Study
Weegar, Rebecka; Hammarlund, Linus; Tegen, Agnes; Oskarsson, Magnus, et al. (2014). Visual Entity Linking: A Preliminary Study Cognitive computing for augmented human intelligence, papers presented at the Twenty-Eighth AAAI Conference on Artificial Intelligence, 46 - 49. AAAI 2014 Workshop on Cognitive Computing for Augmented Human Intelligence: AAAI
Conference Proceeding/Paper
|
Published
|
English
Authors:
Weegar, Rebecka
;
Hammarlund, Linus
;
Tegen, Agnes
;
Oskarsson, Magnus
, et al.
Department:
Mathematics (Faculty of Engineering)
Centre for Mathematical Sciences
Department of Computer Science
ELLIIT: the Linköping-Lund initiative on IT and mobile communication
eSSENCE: The e-Science Collaboration
Robotics and Semantic Systems
Abstract:
In this paper, we describe a system that jointly extracts
entities appearing in images and mentioned in their ac-
companying captions. As input, the entity linking pro-
gram takes a segmented image together with its cap-
tion. It consists of a sequence of processing steps: part-
of-speech tagging, dependency parsing, and coreference
resolution that enables us to identify the entities as well
as possible textual relations from the captions. The pro-
gram uses the image regions labelled with a set of pre-
defined categories and computes WordNet similarities
between these labels and the entity names. Finally, the
program links the entities it detected across the text and
the images. We applied our system on the Segmented
and Annotated IAPR TC-12 dataset that we enriched
with entity annotations and we obtained a correct as-
signment rate of 55.48%
Keywords:
Computer Science ;
Mathematics
Cite this