Biomedical named entity recognition using generalized expectation criteria

Abstract

It is difficult to apply machine learning to a domain which is short of labeled training data, such as biomedical named entity recognition (NER) which remains a challenging task because of its extraordinary complex nomenclature. In this paper, we proposed a semi-supervised method which can train condition random field (CRF) models using generalized expectation (GE) criteria to solve biomedical named entity recognition problem. In the proposed method, instead of ''instance'' labeling, the ''feature'' labeling is applied to get the training data which can save lots of labeling time. Latent Dirichlet Allocation (LDA) model was involved to choose the features for labeling. Experiment results show that the proposed method can dramatically improve the performance of biomedical NER through incorporating unlabeled data by feature labeling.

A Novel Approach for Protein-Named Entity Recognition and Protein-Protein Interaction Extraction

“…Many bionamed entity recognition systems and methods have been proposed. The applied machine learning algorithms are HMM [6,7], SVM [8,9], MEMM [10], CRFs [11][12][13], and so forth. To increase the accuracy of recognition, several researches applied two machine learning algorithms together [9,14].…”

“…Feature Selection and Extraction. Until now, many features for Protein-NER are generated [11]. However, the target bionamed entities are different; the suitable features are different too.…”

Recognizing logical parts in Vietnamese legal texts using Conditional Random Fields

“…Furthermore, CRFs approaches are used sucessfully in many researches in biomedical and chemical fields [10] [11], [12], [13], [14], [18] [19]. In the task of recognizing chemical compounds, [10] presented a tool called ChemSpot which is based on a hybrid approach combining CRFs with a dictionary to recognize chemical compounds in natural language texts, including trivial names, drugs, abbreviations, molecular formulas and International Union of Pure and Applied Chemistry entities.…”