Pro3Gres Parser in the CoNLL Domain Adaptation Shared Task

Pro3Gres Parser in the CoNLL Domain Adaptation Shared Task

inproceedings
Gerold Schneider, Kaarel Kaljurand, Fabio Rinaldi, Tobias Kuhn
We present Pro3Gres, a deep-syntactic, fast dependency parser that combines a handwritten competence grammar with probabilistic performance disambiguation and that has been used in the biomedical domain. We discuss its performance in the domain adaptation open submission. We achieve average results, which is partly due to difficulties in mapping to the dependency representation used for the shared task.
Pro3Gres Parser in the CoNLL Domain Adaptation Shared Task
2007
1161-1165
Prague
June
Proc. of the ACL Conference, Workshop on Computational Natural Language Learning (CoNLL-XI) Shared Task
cl