ChemTok: A New Rule Based Tokenizer for Chemical Named Entity Recognition
Joint Authors
Akkasi, Abbas
Varoğlu, Ekrem
Dimililer, Nazife
Source
Issue
Vol. 2016, Issue 2016 (31 Dec. 2016), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2016-01-28
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
Named Entity Recognition (NER) from text constitutes the first step in many text mining applications.
The most important preliminary step for NER systems using machine learning approaches is tokenization where raw text is segmented into tokens.
This study proposes an enhanced rule based tokenizer, ChemTok, which utilizes rules extracted mainly from the train data set.
The main novelty of ChemTok is the use of the extracted rules in order to merge the tokens split in the previous steps, thus producing longer and more discriminative tokens.
ChemTok is compared to the tokenization methods utilized by ChemSpot and tmChem.
Support Vector Machines and Conditional Random Fields are employed as the learning algorithms.
The experimental results show that the classifiers trained on the output of ChemTok outperforms all classifiers trained on the output of the other two tokenizers in terms of classification performance, and the number of incorrectly segmented entities.
American Psychological Association (APA)
Akkasi, Abbas& Varoğlu, Ekrem& Dimililer, Nazife. 2016. ChemTok: A New Rule Based Tokenizer for Chemical Named Entity Recognition. BioMed Research International،Vol. 2016, no. 2016, pp.1-9.
https://search.emarefa.net/detail/BIM-1097706
Modern Language Association (MLA)
Akkasi, Abbas…[et al.]. ChemTok: A New Rule Based Tokenizer for Chemical Named Entity Recognition. BioMed Research International No. 2016 (2016), pp.1-9.
https://search.emarefa.net/detail/BIM-1097706
American Medical Association (AMA)
Akkasi, Abbas& Varoğlu, Ekrem& Dimililer, Nazife. ChemTok: A New Rule Based Tokenizer for Chemical Named Entity Recognition. BioMed Research International. 2016. Vol. 2016, no. 2016, pp.1-9.
https://search.emarefa.net/detail/BIM-1097706
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1097706