Because the most common transition systems are projective, training a transition-based dependency parser often implies to either ignore or rewrite the non-projective training examples, which has an adverse impact on accuracy. In this work, we propose a simple modification of dynamic oracles, which enables the use of non-projective data when training projective parsers. Evaluation on 73 tree-banks shows that our method achieves significant gains (+2 to +7 UAS for the most non-projective languages) and consistently outperforms traditional projectivization and pseudo-projectivization approaches.
展开▼
