Boosting drug named entity recognition using an aggregate classifier

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Korkontzelos:2015:AIM,

• author = "Ioannis Korkontzelos and Dimitrios Piliouras and Andrew W. Dowsey and Sophia Ananiadou",
• title = "Boosting drug named entity recognition using an aggregate classifier",
• journal = "Artificial Intelligence in Medicine",
• volume = "65",
• number = "2",
• pages = "145--153",
• year = "2015",
• note = "Intelligent healthcare informatics in big data era",
• ISSN = "0933-3657",
• DOI = "doi:10.1016/j.artmed.2015.05.007",
• URL = "http://www.sciencedirect.com/science/article/pii/S0933365715000780",
• abstract = "Objective Drug named entity recognition (NER) is a critical step for complex biomedical NLP tasks such as the extraction of pharmacogenomic, pharmacodynamic and pharmacokinetic parameters. Large quantities of high quality training data are almost always a prerequisite for employing supervised machine-learning techniques to achieve high classification performance. However, the human labour needed to produce and maintain such resources is a significant limitation. In this study, we improve the performance of drug NER without relying exclusively on manual annotations. Methods We perform drug NER using either a small gold-standard corpus (120 abstracts) or no corpus at all. In our approach, we develop a voting system to combine a number of heterogeneous models, based on dictionary knowledge, gold-standard corpora and silver annotations, to enhance performance. To improve recall, we employed genetic programming to evolve 11 regular-expression patterns that capture common drug suffixes and used them as an extra means for recognition. Materials Our approach uses a dictionary of drug names, i.e. DrugBank, a small manually annotated corpus, i.e. the pharmacokinetic corpus, and a part of the UKPMC database, as raw biomedical text. Gold-standard and silver annotated data are used to train maximum entropy and multinomial logistic regression classifiers. Results Aggregating drug NER methods, based on gold-standard annotations, dictionary knowledge and patterns, improved the performance on models trained on gold-standard annotations, only, achieving a maximum F-score of 95percent. In addition, combining models trained on silver annotations, dictionary knowledge and patterns are shown to achieve comparable performance to models trained exclusively on gold-standard data. The main reason appears to be the morphological similarities shared among drug names. Conclusion We conclude that gold-standard data are not a hard requirement for drug NER. Combining heterogeneous models build on dictionary knowledge can achieve similar or comparable classification performance with that of the best performing model trained on gold-standard annotations.",
• keywords = "genetic algorithms, genetic programming, Named entity annotation sparsity, Gold-standard vs. silver-standard annotations, Named entity recogniser aggregation, Genetic-programming-evolved string-similarity patterns, Drug named entity recognition",

}

Genetic Programming entries for Ioannis Korkontzelos Dimitrios Piliouras Andrew Dowsey Sophia Ananiadou

Citations