Paper: A Second-Order Joint Eisner Model for Syntactic and Semantic Dependency Parsing

ACL ID W09-1212
Title A Second-Order Joint Eisner Model for Syntactic and Semantic Dependency Parsing
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
Authors

We present a system developed for the CoNLL-2009 Shared Task (Hajiˇc et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic depen- dencies. This state-of-the-art parser factor- izes 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 seman- tic F1.