Paper Info
Title
Bio Named Entity Recognition Based on Co-training Algorithm
Abstract
One essential task in extracting information from biomedical literature is the bio Named Entity Recognition (NER) process, which basically defines the boundaries between typical words and biomedical terminology in particular text data, and assigns them based on domain knowledge. This paper presents a semi supervised integration of completely different classifiers to cover knowledge from unlabeled data to recognize bio named entities in text. We modified the original co-training, a semi supervised learning algorithm, with a scalable feature processing schema, which extracts the bio NER feature from a number of unlabeled data and converts different types of feature sets. Our base result shows that the classifiers of co-training achieve significant learning from unlabeled data.
Year
DOI
Venue
2012
10.1109/WAINA.2012.75
AINA Workshops
Keywords
Field
DocType
different classifier,bio ner feature,feature set,co-training algorithm,entity recognition,biomedical literature,scalable feature processing schema,particular text data,domain knowledge,different type,unlabeled data,biomedical terminology,feature extraction,text mining,information extraction,semi supervised learning,dictionaries,bioinformatics,classification algorithms,text analysis,data mining,learning artificial intelligence
Semi-supervised learning,Terminology,Pattern recognition,Domain knowledge,Computer science,Algorithm,Co-training,Feature extraction,Artificial intelligence,Statistical classification,Named-entity recognition,Scalability
Conference
Citations 
PageRank 
References 
7
0.45
14
Authors
7
Name
Order
Citations
PageRank
Tsendsuren Munkhdalai116913.49
Meijing Li2507.60
Taewook Kim3224.67
Oyun-erdene Namsrai4244.32
Seon-phil Jeong5182.84
Jungpil Shin66324.26
Keun Ho Ryu788385.61