Mapping CPA Patterns onto OntoNotes Senses
Octavian Popescu, Martha Stone Palmer, Patrick Hanks · 2014
In this paper we present an alignment experiment between patterns of verb use discovered by Corpus Pattern Analysis (CPA;Hanks 2004Hanks , 2008Hanks , 2013) ) and verb senses in OntoNotes (ON;Hovy et al. 2006, Weischedel et al. 2011).We present a probabilistic approach for mapping one resource into the other.Firstly we introduce a basic model, based on conditional probabilities, which determines for any given sentence the best CPA pattern match.On the basis of this model, we propose a joint source channel model (JSCM) that computes the probability of compatibility of semantic types between a verb phrase and a pattern, irrespective of whether the verb phrase is a norm or an exploitation.We evaluate the accuracy of the proposed mapping using cluster similarity metrics based on entropy.