Experiments with a Higher-Order Projective Dependency Parser

9 years 2 months ago
Experiments with a Higher-Order Projective Dependency Parser
We present experiments with a dependency parsing model defined on rich factors. Our model represents dependency trees with factors that include three types of relations between the tokens of a dependency and their children. We extend the projective parsing algorithm of Eisner (1996) for our case, and train models using the averaged perceptron. Our experiments show that considering higher-order information yields significant improvements in parsing accuracy, but comes at a high cost in terms of both time and memory consumption. In the multilingual exercise of the CoNLL-2007 shared task (Nivre et al., 2007), our system obtains the best accuracy for English, and the second best accuracies for Basque and Czech.
Xavier Carreras
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2007
Authors Xavier Carreras
Comments (0)