WBI-NER: The impact of domain-specific features on the performance of identifying and classifying mentions of drugs

Named entity recognition (NER) systems are often based on machine learning techniques to reduce the labor-intensive development of hand-crafted extraction rules and domain-dependent dictionaries. Nevertheless, time-consuming feature engineering is often needed to achieve state-of-the-art performance. In this study, we investigate the impact of such domain-specific features on the performance of recognizing and classifying mentions of pharmacological substances. We compare the performance of a system based on general features, which have been successfully applied to a wide range of NER tasks, with a system that additionally uses features generated from the output of an existing chemical NER tool and a collection of domain-specific resources. We demonstrate that acceptable results can be achieved with the former system. Still, our experiments show that using domain-specific features outperforms this general approach. Our system ranked first in the SemEval-2013 Task9.1: Recognition and classification of pharmacological substances.

help Contributors

[Tim Rocktäschel] [Michael Weidlich] [Ulf Leser]

help Other Contributors

Torsten Huber

help Attributions


help Scales

Views: 981
  • Created: 16th Dec 2013 at 09:53
  • Last used: 20th Mar 2018 at 01:20

Related items


Log in / Register

Need an account?
Sign up

Forgotten password?

Front Page

Virtual Liver Network


Related Projects and friends

Imprint Taverna workflow workbench myExperiment JWS Online ISATAB myGrid Sabio-RK BioPortal Semantic SBML

Powered by:


Silk icons 1.3
Crystal Clear icons