Paper: Bootstrapping Biomedical Ontologies for Scientific Text using NELL

ACL ID W12-2402
Title Bootstrapping Biomedical Ontologies for Scientific Text using NELL
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2012
Authors

We describe an open information extraction system for biomedical text based on NELL (the Never-Ending Language Learner) (Carl- son et al., 2010), a system designed for ex- traction from Web text. NELL uses a cou- pled semi-supervised bootstrapping approach to learn new facts from text, given an initial ontology and a small number of ?seeds? for each ontology category. In contrast to previ- ous applications of NELL, in our task the ini- tial ontology and seeds are automatically de- rived from existing resources. We show that NELL?s bootstrapping algorithm is suscepti- ble to ambiguous seeds, which are frequent in the biomedical domain. Using NELL to ex- tract facts from biomedical text quickly leads to semantic drift. To address this problem, we introduce a method for assessing seed qual- i...