Abstract
This paper presents an approach for word sense disambiguation (WSD) of image tags from professional and social image databases without categorial labels, using WordNet as an external resource defining word senses. We focus on the resolution of lexical ambiguity that arises when a given keyword has several different meanings. Our approach combines some knowledge-based methods (Lesk algorithm and Hyponym Heuristics) and semantic measures, in order to achieve successful disambiguation. Experimental results and performance evaluation are 95.16 % accuracy for professional images and 87.40 % accuracy for social images, for keywords included in WordNet. This approach can be used for improving machine translation of tags or image similarity measurement.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
