Extracting events of biomedical relevance from text
5The understanding of e.g. multifactorial diseases requires the discovery of entities and their relationships from several domains: proteomics, metabolomics, toxicology, etc. The evidence to generate hypotheses for comprehensive diagnostics, interventions, treatments, etc is hidden in text. In addition, the type of evidence needed is complex, requiring techniques beyond statistical keyword search mechanisms. Event extraction techniques can represent such complex associations which can trace cause and effect across multiple levels of biological organisation while also providing other contextual information such as negation, speculation, etc. Event extraction results have been incorporated into recent text search engines to support advanced tasks such as pathway curation. Curation environments such as Argo, faciliate the task of annotation.