%0 Generic %1 Petasis00c.:symbolic %A Petasis, Georgios %A Petridis, Sergios %A Paliouras, Georgios %A Karkaletsis, Vangelis %A Perantonis, Stavros J. %A Spyropoulos, Constantine D. %B Proceedings of European Best Practice Workshops and Symposium on Computational Intelligence and Learning (COIL 2000) %C Chios, Greece %D 2000 %K entity induction, name networks neural recognition, tree %P 58--66 %T Symbolic and Neural Learning for Named-Entity Recognition %U http://www.ellogon.org/petasis/bibliography/COIL2000/COIL-2000.pdf %X Named-entity recognition involves the identification and classification of named entities in text. This is an important subtask in most language engineering applications, in particular information extraction, where different types of named entity are associated with specific roles in events. The manual construction of rules for the recognition of named entities is a tedious and time-consuming task. For this reason, we present in this paper two approaches to learning named-entity recognition rules from text. The first approach is a decision-tree induction method and the second a multi-layered feed-forward neural network. Particular emphasis is paid on the selection of the appropriate feature set for each method and the extraction of training examples from unstructured textual data. We compare the performance of the two methods on a large corpus of English text and present the results.

@conference{Petasis00c.:symbolic, abstract = {Named-entity recognition involves the identification and classification of named entities in text. This is an important subtask in most language engineering applications, in particular information extraction, where different types of named entity are associated with specific roles in events. The manual construction of rules for the recognition of named entities is a tedious and time-consuming task. For this reason, we present in this paper two approaches to learning named-entity recognition rules from text. The first approach is a decision-tree induction method and the second a multi-layered feed-forward neural network. Particular emphasis is paid on the selection of the appropriate feature set for each method and the extraction of training examples from unstructured textual data. We compare the performance of the two methods on a large corpus of English text and present the results.}, added-at = {2011-08-10T12:37:26.000+0200}, address = {Chios, Greece}, author = {Petasis, Georgios and Petridis, Sergios and Paliouras, Georgios and Karkaletsis, Vangelis and Perantonis, Stavros J. and Spyropoulos, Constantine D.}, biburl = {https://www.bibsonomy.org/bibtex/2af8fa570b5ed25ac62113ea17ffad01d/petasis}, booktitle = {Proceedings of European Best Practice Workshops and Symposium on Computational Intelligence and Learning (COIL 2000)}, interhash = {c42ca96a4f984fd09cea763b56c737f0}, intrahash = {af8fa570b5ed25ac62113ea17ffad01d}, keywords = {entity induction, name networks neural recognition, tree}, month = {June 19--23}, pages = {58--66}, timestamp = {2011-08-10T12:37:27.000+0200}, title = {{S}ymbolic and {N}eural {L}earning for {N}amed-{E}ntity {R}ecognition}, url = {http://www.ellogon.org/petasis/bibliography/COIL2000/COIL-2000.pdf}, year = 2000 }