@article {15320, title = {Concept disambiguation for improved subject access using multiple knowledge sources}, journal = {Proceedings of the Workshop on Language Technology for Cultural Heritage Data (LaTeCH 2007)}, year = {2007}, month = {2007///}, pages = {25 - 25}, abstract = {We address the problem of mining text forrelevant image metadata. Our work is situ- ated in the art and architecture domain, where highly specialized technical vocabu- lary presents challenges for NLP tech- niques. To extract high quality metadata, the problem of word sense disambiguation must be addressed in order to avoid leading the searcher to the wrong image as a result of ambiguous{\textemdash}and thus faulty{\textemdash}meta- data. In this paper, we present a disam- biguation algorithm that attempts to select the correct sense of nouns in textual de- scriptions of art objects, with respect to a rich domain-specific thesaurus, the Art and Architecture Thesaurus (AAT). We per- formed a series of intrinsic evaluations us- ing a data set of 600 subject terms ex- tracted from an online National Gallery of Art (NGA) collection of images and text. Our results showed that the use of external knowledge sources shows an improvement over a baseline. }, author = {Sidhu,T. and Klavans,J. and Jimmy Lin} }