Improving a State-of-the-Art Named Entity Recognition System Using the World Wide Web Export

@incollection{citeulike:2251085, abstract = {The development of highly accurate Named Entity Recognition (NER) systems can be beneficial to a wide range of Human Language Technology applications. In this paper we introduce three heuristics that exploit a variety of knowledge sources (the World Wide Web, Wikipedia and WordNet) and are capable of improving further a state-of-the-art multilingual and domain independent NER system. Moreover we describe our investigations on entity recognition in simulated speech-to-text output. Our web-based heuristics attained a slight improvement over the best results published on a standard NER task, and proved to be particularly effective in the speech-to-text scenario.}, author = {Farkas, Rich\'{a}rd and Szarvas, Gy\"{o}rgy and Orm\'{a}ndi, R\'{o}bert}, citeulike-article-id = {2251085}, citeulike-linkout-0 = {http://dblp.uni-trier.de/rec/bibtex/conf/incdm/FarkasSO07}, citeulike-linkout-1 = {http://dx.doi.org/10.1007/978-3-540-73435-2_13}, doi = {10.1007/978-3-540-73435-2_13}, journal = {Advances in Data Mining. Theoretical Aspects and Applications}, keywords = {ie, textmining}, pages = {163--172}, posted-at = {2008-02-22 00:59:12}, priority = {2}, title = {Improving a State-of-the-Art Named Entity Recognition System Using the World Wide Web}, url = {http://dx.doi.org/10.1007/978-3-540-73435-2_13}, year = {2007} }

TY - CHAP ID - citeulike:2251085 L3 - citeulike-article-id:2251085 N2 - The development of highly accurate Named Entity Recognition (NER) systems can be beneficial to a wide range of Human Language Technology applications. In this paper we introduce three heuristics that exploit a variety of knowledge sources (the World Wide Web, Wikipedia and WordNet) and are capable of improving further a state-of-the-art multilingual and domain independent NER system. Moreover we describe our investigations on entity recognition in simulated speech-to-text output. Our web-based heuristics attained a slight improvement over the best results published on a standard NER task, and proved to be particularly effective in the speech-to-text scenario. JF - Advances in Data Mining. Theoretical Aspects and Applications EP - 172 TI - Improving a State-of-the-Art Named Entity Recognition System Using the World Wide Web SP - 163 KW - ie KW - textmining AU - Farkas, Richárd AU - Szarvas, György AU - Ormándi, Róbert PY - 2007/// UR - http://dx.doi.org/10.1007/978-3-540-73435-2_13 ER -