Biological event recognition with textual induction

Yutaka Sasaki, Paul Thompson, John McNaught, Sophia Ananiadou

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


    This paper describes a supervised approach to the recognition of biological events, which combines statistical sequential labelling and symbolic event extractionrules. Bottom-up textual induction has been applied to generating eventextraction rules. As an evaluation data set, we use a corpus of biomedical abstracts, in which biological events concerning gene regulation in E. coli and H. Sapiens have been annotated by a group of biologists. The event instance extraction performance has been evaluated using 10- fold cross validation. The experimental results show that named entity recognition (NER) and semantic role labelling (SRL) performance are close to annotator performance, as indicated by the interannotator agreement (IAA) scores, whereas automatic event extraction performance is around 28%, as compared to 40% IAA for exact manual event extraction.
    Original languageEnglish
    Title of host publicationProceedings of the 3rd International Symposium on Languages in Biology and Medicine (LBM-2009)
    Number of pages6
    Publication statusPublished - 2009
    Event3rd International Symposium on Languages in Biology and Medicine (LBM-2009) -
    Duration: 1 Jan 1824 → …


    Conference3rd International Symposium on Languages in Biology and Medicine (LBM-2009)
    Period1/01/24 → …


    • text mining
    • biology
    • event extraction
    • predicate argument structure
    • machine learning


    Dive into the research topics of 'Biological event recognition with textual induction'. Together they form a unique fingerprint.

    Cite this