The effect of semi-supervised learning on parsing long distance dependencies in German and Swedish

TY - GEN

T1 - The effect of semi-supervised learning on parsing long distance dependencies in German and Swedish

AU - Søgaard, Anders Østerskov

AU - Rishøj, Christian

PY - 2010

Y1 - 2010

N2 - This paper shows how the best data-driven dependency parsers available today [1] can be improved by learning from unlabeled data. We focus on German and Swedish and show that labeled attachment scores improve by 1.5%-2.5%. Error analysis shows that improvements are primarily due to better recovery of long distance dependencies.

AB - This paper shows how the best data-driven dependency parsers available today [1] can be improved by learning from unlabeled data. We focus on German and Swedish and show that labeled attachment scores improve by 1.5%-2.5%. Error analysis shows that improvements are primarily due to better recovery of long distance dependencies.

M3 - Article in proceedings

SN - 3-642-14769-0 978-3-642-14769-2

BT - Proceedings of the 7th International Conference on Advances in Natural Language Processing

PB - Springer

ER -