SCAI: Extracting drug-drug interactions using a rich feature vector
Tamara Bobić, Juliane Fluck, Martin Hofmann‐Apitius
Abstract
Automatic relation extraction provides great support for scientists and database curators in dealing with the extensive amount of biomedical textual data. The DDIExtraction 2013 challenge poses the task of detecting drug drug interactions and further categorizing them into one of the four relation classes. We present our machine learning system which utilizes lexical, syntactical and semantic based feature sets. Resampling, balancing and ensemble learning experiments are performed to infer the best configuration. For general drug drug relation extraction, the system achieves 70.4% in F1 score.
Topics & Concepts
Computer scienceRelation (database)Relationship extractionResamplingTask (project management)Artificial intelligenceFeature extractionSupport vector machineFeature (linguistics)Machine learningNatural language processingFeature vectorPattern recognition (psychology)Data miningEngineeringSystems engineeringPhilosophyLinguisticsBiomedical Text Mining and OntologiesAdvanced Text Analysis TechniquesTopic Modeling