Weighted Mutual Exclusion Bootstrapping for Domain Independent Lexicon and Template Acquisition
Tara McIntosh, James Curran · 2008
We present the Weighted Mutual Exclusion Bootstrapping (WMEB) algorithm for simultaneously extracting precise semantic lexicons and templates for multiple categories. WMEB is capable of extracting larger lexicons with higher precision than previous techniques, successfully reducing semantic drift by incorporating new weighting functions and a cumulative template pool while still enforcing mutual exclusion between the categories. We compare WMEB and two state-of-theart approaches on the Web 1T corpus and two large biomedical literature collections. WMEB is more efficient and scalable, and we demonstrate that it significantly outperforms the other approaches on the noisy web corpus and biomedical text. 1