A high-performance semi-supervised learning method for text chunking Export

@inproceedings{citeulike:1743195, abstract = {In machine learning, whether one can build a more accurate classifier by using unlabeled data ( semi-supervised learning ) is an important issue. Although a number of semi-supervised methods have been proposed, their effectiveness on NLP tasks is not always clear. This paper presents a novel semi-supervised method that employs a learning paradigm which we call structural learning . The idea is to find "what good classifiers are like" by learning from thousands of automatically generated auxiliary classification problems on unlabeled data. By doing so, the common predictive structure shared by the multiple classification problems can be discovered, which can then be used to improve performance on the target problem. The method produces performance higher than the previous best results on CoNLL'00 syntactic chunking and CoNLL'03 named entity chunking (English and German).}, address = {Morristown, NJ, USA}, author = {Ando, Rie K. and Zhang, Tong}, booktitle = {ACL '05: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics}, citeulike-article-id = {1743195}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1219841}, citeulike-linkout-1 = {http://dx.doi.org/10.3115/1219840.1219841}, doi = {10.3115/1219840.1219841}, keywords = {aso, chunking, extraction, information, semi-supervised, text}, location = {Ann Arbor, Michigan}, pages = {1--9}, posted-at = {2009-09-24 14:10:33}, priority = {2}, publisher = {Association for Computational Linguistics}, title = {A high-performance semi-supervised learning method for text chunking}, url = {http://dx.doi.org/10.3115/1219840.1219841}, year = {2005} }

TY - CONF ID - citeulike:1743195 L3 - citeulike-article-id:1743195 N2 - In machine learning, whether one can build a more accurate classifier by using unlabeled data ( semi-supervised learning ) is an important issue. Although a number of semi-supervised methods have been proposed, their effectiveness on NLP tasks is not always clear. This paper presents a novel semi-supervised method that employs a learning paradigm which we call structural learning . The idea is to find "what good classifiers are like" by learning from thousands of automatically generated auxiliary classification problems on unlabeled data. By doing so, the common predictive structure shared by the multiple classification problems can be discovered, which can then be used to improve performance on the target problem. The method produces performance higher than the previous best results on CoNLL'00 syntactic chunking and CoNLL'03 named entity chunking (English and German). CY - Ann Arbor, Michigan AD - Morristown, NJ, USA EP - 9 TI - A high-performance semi-supervised learning method for text chunking PB - Association for Computational Linguistics T2 - ACL '05: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics SP - 1 KW - aso KW - chunking KW - extraction KW - information KW - semi-supervised KW - text AU - Ando, Rie AU - Zhang, Tong PY - 2005/// UR - http://dx.doi.org/10.3115/1219840.1219841 ER -