Tuning Support Vector Machines for Biomedical Named Entity Recognition

DMCA

Tuning Support Vector Machines for Biomedical Named Entity Recognition (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Jun'ichi Kazama Takaki , Takaki Makino , Yoshihiro Ohta

Venue:

In Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain

BibTeX

@INPROCEEDINGS{Takaki02tuningsupport,
    author = {Jun'ichi Kazama Takaki and Takaki Makino and Yoshihiro Ohta},
    title = {Tuning Support Vector Machines for Biomedical Named Entity Recognition},
    booktitle = {In Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain},
    year = {2002},
    pages = {1--8}
}

OpenURL

Abstract

We explore the use of Support Vector Machines (SVMs) for biomedical named entity recognition. To make the SVM training with the available largest corpus -- the GENIA corpus -- tractable, we propose to split the non-entity class into sub-classes, using part-of-speech information. In addition, we explore new features such as word cache and the states of an HMM trained by unsupervised learning. Experiments on the GENIA corpus show that our class splitting technique not only enables the training with the GENIA corpus but also improves the accuracy. The proposed new features also contribute to improve the accuracy. We compare our SVMbased recognition system with a system using Maximum Entropy tagging method.

Keyphrases

support vector machine biomedical named entity recognition genia corpus new feature genia corpus show non-entity class part-of-speech information entity recognition class splitting technique svmbased recognition system maximum entropy word cache svm training unsupervised learning

DMCA