Paper: HITS-based Seed Selection and Stop List Construction for Bootstrapping

ACL ID P11-2006
Title HITS-based Seed Selection and Stop List Construction for Bootstrapping
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

In bootstrapping (seed set expansion), select- ing good seeds and creating stop lists are two effective ways to reduce semantic drift, but these methods generally need human super- vision. In this paper, we propose a graph- based approach to helping editors choose ef- fective seeds and stop list instances, appli- cable to Pantel and Pennacchiotti’s Espresso bootstrapping algorithm. The idea is to select seeds and create a stop list using the rankings of instances and patterns computed by Klein- berg’s HITS algorithm. Experimental results on a variation of the lexical sample task show the effectiveness of our method.