Paper: Filtered Ranking for Bootstrapping in Event Extraction

ACL ID C10-1077
Title Filtered Ranking for Bootstrapping in Event Extraction
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2010

Several researchers have proposed semi-supervised learning methods for adapting event extraction systems to new event types. This paper investigates two kinds of bootstrapping methods used for event extraction: the document-centric and similarity-centric approaches, and proposes a filtered ranking method that combines the advantages of the two. We use a range of extraction tasks to compare the generality of this method to previous work. We analyze the results using two evaluation metrics and observe the efect of diferent training corpora. Experiments show that our new ranking method not only achieves higher performance on diferent evaluation metrics, but also is more stable acros diferent bootstrapping corpora.