A second-order joint Eisner model for syntactic and semantic dependency parsing
Document typeConference lecture
Rights accessRestricted access - publisher's policy
We present a system developed for the CoNLL-2009 Shared Task (Hajic et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.
CitationLluis, X.; Bott, S.; Màrquez, L. A second-order joint Eisner model for syntactic and semantic dependency parsing. A: Conference on Natural Language Learning. "Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009)". 2009, p. 79-84.
|W09-1212.pdf||A Second-Order Joint Eisner Model for Syntactic and Semantic Dependency Parsing||140.9Kb||Restricted access|