The nature of statistical learning theory
The nature of statistical learning theory
Making large-scale support vector machine learning practical
Advances in kernel methods
Feature selection in SVM text categorization
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Introduction to the CoNLL-2003 shared task: language-independent named entity recognition
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
| Hi-index | 0.00 |
Named Entity Recognition and Classification (NERC) is one of the most fundamental and important tasks in biomedical information extraction. Gene mention detection is concerned with the named entity (NE) extraction of gene and gene product mentions in text. Several different approaches have emerged but most of these state-of-the-art approaches suggest that individual NERC system may not cover entity representations with arbitrary set of features and cannot achieve best performance. In this paper, we propose a voted approach for gene mention detection. We use support vector machine (SVM) as the underlying classification methodology, and build different models of it depending upon the various representations of the set of features. One most important criterion of these features is that these are identified and selected largely without using any domain knowledge. Evaluation results with the benchmark dataset of GENTAG yields the state-of-the-art performance with the overall recall, precision and F-measure values of 94.95%, 94.32%, and 94.63%, respectively.