Annotating Documents by Wikipedia Concepts Export

@inproceedings{citeulike:5304020, abstract = {We present a technique which is able to reliably label words or phrases of an arbitrary document with Wikipedia articles (concepts) best describing their meaning. First it scans the document content, and when it finds a word sequence matching the title of a Wikipedia article, it attaches the article to the constituent word(s). The collected articles are then scored based on three factors: (1) how many other detected articles they semantically relate to, according to the Wikipedia link structure; (2) how specific is the concept they represent; and (3) how similar is the title by which they were detected to their "official" title. If a text location refers to multiple Wikipedia articles, only the one with the highest score is retained. Experiments on 24,000 randomly selected Wikipedia article bodies showed that 81\% of phrases annotated by article authors were correctly identified. Moreover, out of the 5 concepts deemed as the most important by our algorithm during a final ranking, in average 72\% was indeed marked in the original text.}, author = {Schonhofen, P.}, booktitle = {Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on}, citeulike-article-id = {5304020}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/WIIAT.2008.56}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4740493}, doi = {10.1109/WIIAT.2008.56}, journal = {Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on}, keywords = {categorization--automatic, wikipedia--nlp\_resource}, pages = {461--467}, posted-at = {2009-07-30 15:30:52}, priority = {2}, title = {Annotating Documents by Wikipedia Concepts}, url = {http://dx.doi.org/10.1109/WIIAT.2008.56}, volume = {1}, year = {2008} }

TY - CONF ID - citeulike:5304020 L3 - citeulike-article-id:5304020 N2 - We present a technique which is able to reliably label words or phrases of an arbitrary document with Wikipedia articles (concepts) best describing their meaning. First it scans the document content, and when it finds a word sequence matching the title of a Wikipedia article, it attaches the article to the constituent word(s). The collected articles are then scored based on three factors: (1) how many other detected articles they semantically relate to, according to the Wikipedia link structure; (2) how specific is the concept they represent; and (3) how similar is the title by which they were detected to their "official" title. If a text location refers to multiple Wikipedia articles, only the one with the highest score is retained. Experiments on 24,000 randomly selected Wikipedia article bodies showed that 81% of phrases annotated by article authors were correctly identified. Moreover, out of the 5 concepts deemed as the most important by our algorithm during a final ranking, in average 72% was indeed marked in the original text. JF - Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on EP - 467 TI - Annotating Documents by Wikipedia Concepts VL - 1 T2 - Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on SP - 461 KW - categorization--automatic KW - wikipedia--nlp_resource AU - Schonhofen, P PY - 2008/// UR - http://dx.doi.org/10.1109/WIIAT.2008.56 ER -