Using Treebanking Discriminants as Parse Disambiguation Features

Faisal Mahbub Chowdhury, Yi Zhang, Valia Kordoni

In: Éric Villemonte de la Clergerie , Harry Bunt (Hrsg.). Proceedings of the 11th International Conference on Parsing Technologies 2009. International Conference on Parsing Technologies (IWPT-09) October 7-9 Paris France IWPT 2009.


This paper presents a novel approach of incorporating fine-grained treebanking decisions made by human annotators as discriminative features for automatic parse disambiguation. To our best knowledge, this is the first work that exploits treebanking decisions for this task. The advantage of this approach is that use of human judgements is made. The paper presents comparative analyses of the performance of discriminative models built using treebanking decisions and state-of-the-art features. We also highlight how differently these features scale when these models are tested on out-of-domain data. We show that, features extracted using treebanking decisions are more efficient, informative and robust compared to traditional features.


Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence