Publikation
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.
Zusammenfassung
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.