Paper: An Ensemble Model that Combines Syntactic and Semantic Clustering for Discriminative Dependency Parsing

ACL ID P11-2125
Title An Ensemble Model that Combines Syntactic and Semantic Clustering for Discriminative Dependency Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

We combine multiple word representations based on semantic clusters extracted from the (Brown et al., 1992) algorithm and syntac- tic clusters obtained from the Berkeley parser (Petrov et al., 2006) in order to improve dis- criminative dependency parsing in the MST- Parser framework (McDonald et al., 2005). We also provide an ensemble method for com- bining diverse cluster-based models. The two contributions together significantly improves unlabeled dependency accuracy from 90.82% to 92.13%.