Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees

Lauriane Aufrant, Guillaume Wisniewski, François Yvon

Abstract:

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~treebanks 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.