A Simple, Similarity-based Model for Selectional Preferences

Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 216–223, Prague, Czech Republic, June 2007. c⃝2007 Association for Computational Linguistics A Simple, Similarity-based Model for Selectional Preferences Katrin Erk University of Texas at Austin katrin.erk@mail.utexas.edu Abstract We propose a new, simple model for the auto- matic induction of selectional preferences, using corpus-based semantic similarity metrics. Fo- cusing on the task of semantic role labeling, we compute selectional preferences for seman- tic roles. In evaluations the similarity-based model shows lower error rates than both Resnik’s WordNet-based model and the EM-based clus- tering model, but has coverage problems. 1 Introduction Selectional preferences, which characterize typ- ical arguments of predicates, are a very use- ful and versatile knowledge source. They have been used for example for syntactic disambigua- tion (Hindle and Rooth, 1993), word sense dis- ambiguation (WSD) (McCarthy and Carroll, 2003) and semantic role labeling (SRL) (Gildea and Jurafsky, 2002). The corpus-based induction of selectional preferences was first proposed by Resnik (1996). All later approaches have followed the same two- step procedure, first collecting argument head- words from a corpus, then generalizing to other, similar words. Some approaches have used WordNet for the generalization step (Resnik, 1996; Clark and Weir, 2001; Abe and Li, 1993), others EM-based clustering (Rooth et al., 1999). In this paper we propose a new, simple model for selectional preference induction that uses corpus-based semantic similarity metrics, such as Cosine or Lin’s (1998) mutual information- based metric, for the generalization step. This model does not require any manually created lexical resources. In addition, the corpus for computing the similarity metrics can be freely chosen, allowing greater variation in the domain of generalization than a fixed lexical resource. We focus on one application of selectional preferences: semantic role labeling. The ar- gument positions for which we compute selec- tional preferences will be semantic roles in the FrameNet (Baker et al., 1998) paradigm, and the predicates we consider will be semantic classes of words rather than individual words (which means that different preferences will be learned for different senses of a predicate word). In SRL, the two most pressing issues today are (1) the development of strong semantic features to complement the current mostly syntactically- based systems, and (2) the problem of the do- main dependence (Carreras and Marquez, 2005). In the CoNLL-05 shared task, participating sys- tems showed about 10 points F-score difference between in-domain and out-of-domain test data. Concerning (1), we focus on selectional prefer- ences as the strongest candidate for informative semantic features. Concerning (2), the corpus- based similarity metrics that we use for selec- tional preference induction open up interesting possibilities of mixing domains. We evaluate the similarity-based model against Resnik’s WordNet-based model as well as the EM-based clustering approach. In the evaluation, the similarity-model shows lower er- ror rates than both Resnik’s WordNet-based model and the EM-based clustering model. However, the EM-based clustering model has higher coverage than both other paradigms. Plan of the paper. After discussing previ- 216 ous approaches …

Content truncated to 500 words