Abstract
We use SVM classifiers to predict the next action of a deterministic parser that builds labeled projective dependency graphs in an incremental fashion. Non-projective dependencies are captured indirectly by projectivizing the training data for the classifiers and applying an inverse transformation to the output of the parser. We present evaluation results and an error analysis focusing on Swedish and Turkish.
Original language | English |
---|---|
Publication status | Published - 2006 |
Event | 10th Conference on Computational Natural Language Learning, CoNLL-X - New York, NY, United States Duration: 8 Jun 2006 → 9 Jun 2006 |
Conference
Conference | 10th Conference on Computational Natural Language Learning, CoNLL-X |
---|---|
Country/Territory | United States |
City | New York, NY |
Period | 8/06/06 → 9/06/06 |