SVM-Based Biological Named Entity Recognition Using Minimum Edit-Distance Feature Boosted by Virtual Examples

In this paper, we propose two indepentent solutions to resolve the problems of many different spelling variants and of lack of annotated corpus for training, which are two main difficulties in SVM(Support-Vector Machine) and other machine-learning based biological named entity recognition. To resolve the problem of spelling variants, we propose a use of edit-distance as a feature for SVM. We also propose a use of virtual examples to automatically expand the annotated corpus to resolve the lack-of-corpus problem. Using virtual examples, the annotated corpus can be expanded in a fast, efficient and easy way. The experimental results

• Type: Conference
• Year: 2004
• Where: IJCNLP
• Authors: Eunji Yi, Gary Geunbae Lee, Yu Song, Soo-Jun Park
• Keywords: Annotated Corpus, IJCNLP 2004, Spelling Variants, Virtual Examples