Tuning support vector machines for biomedical named entity recognition

By Jun'ichi Kazama, Takaki Makino, Yoshihiro Ohta, Junichi Tsujii. ACL Workshop on Natural Language Processing in the Biomedical Domain, 2002

299 citations recorded by the source corpus.

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 SVM-based recognition system with a system using Maximum Entropy tagging method.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/5280e81acc40ec93c27cea07979a991bba60aa96

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Term identification in the biomedical literature (2004, methodology): “Kazama and colleagues [35] trained multi-class SVMs on the GENIA corpus.”
Text mining and ontologies in biomedicine: Making sense of raw text (2005, methodology): “…the training or testing set for different TM tasks: 55 e.g. NER 5 using methods such as hidden Markov models, 56,57 naive Bayes classification, 41,44 maximum entropy, 58,59 conditional random field, 60,61 support vector machines, 62,63 decision trees, 64 combination of different heuristics 65 etc.”
A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques (2017, background): “Naive Bayes [107] and Support Vector Machines [83, 102, 134] are among the common classifiers used for biomedical NER task.”
Biomedical text mining and its applications in cancer research (2013, unknown): “[23] used SVMs to identify protein, DNA, cell-type, cell-line, and lipid, with a 73.”
Unsupervised Learning of Semantic Relations between Concepts of a Molecular Biology Ontology (2005, background): “In this respect the GENIA corpus is unique in that it provides extensive namedentity annotations which can be used to train appropriate NER systems (cf. [Kazama et al., 2002] .”
Corpus annotation for mining biomedical events from literature (2008, methodology): “As with the POS and tree annotations, the term annotation of the GENIA corpus has been widely used for training NLP tools such as Named Entity Recognizers (NERs) [40-44].”
Simple tricks for improving pattern-based information extraction from the biomedical literature (2010, background): “In general, machine learning-based methods to RE perform very well for any task where sufficient and high-quality training data is available [6,7].”