Dealing with data sparsity in drug named entity recognition

Dimitrios Piliouras, Ioannis Korkontzelos, Andrew Dowsey, Sophia Ananiadou

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

1 Citation (Scopus)

Abstract

Drug Named Entity Recognition (drug-NER) is a critical step for complex Biomedical Natural Language Processing (BioNLP) tasks such as the extraction of pharmaco-genomic, pharmaco-dynamic and pharmaco-kinetic parameters. Large quantities of high quality training data are almost always a prerequisite for employing supervised machine-learning (ML) techniques to achieve high classification performance. However, the human labour needed to produce and maintain such resources is a detrimental limitation. In this study, we attempt to improve the performance of drug NER without relying exclusively on manual annotations. Instead, we use either a small gold-standard corpus (120 abstracts) or no corpus at all. In our approach, we use a \emph{voting system} to combine a number of heterogeneous models to enhance performance. Moreover, 11 regular-expressions that capture common drug suffixes were evolved via genetic-programming. We evaluate our approach against state-of-the-art recognisers trained on manual annotations, automatic annotations and a mixture of both. Aggregate classifiers are shown to improve performance, achieving a maximum F-score of 95%. In addition, combined models trained on mixed data are shown to achieve comparable performance to models trained exclusively on gold-standard data.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Healthcare Informatics, ICHI 2013
Pages14-21
Number of pages8
DOIs
Publication statusPublished - 2013
Event2013 1st IEEE International Conference on Healthcare Informatics, ICHI 2013 - Philadelphia, PA, United States
Duration: 9 Sep 201311 Sep 2013

Conference

Conference2013 1st IEEE International Conference on Healthcare Informatics, ICHI 2013
CountryUnited States
CityPhiladelphia, PA
Period9/09/1311/09/13

Structured keywords

  • Jean Golding

Keywords

  • Data-sparsity
  • Drug-NER
  • Genetic-programming

Fingerprint Dive into the research topics of 'Dealing with data sparsity in drug named entity recognition'. Together they form a unique fingerprint.

Cite this