Probabilistic model for syntactic and semantic dependency parsing
Enhong Chen, Liu Shi, Dawei Hu · 2008
This paper proposes a novel method to analyze syntactic dependencies and label semantic dependencies around both the verbal predicates and the nouns. In this method, a probabilistic model is designed to obtain a global optimal result. Moreover, a predicate identification model and a disambiguation model are proposed to label predicates and their senses. The experimental results obtained on the waj and brown test sets show that our system obtains 77% of labeled macro F1 score for the whole task, 84.47% of labeled attachment score for syntactic dependency task, and 69.45% of labeled F1 score for semantic dependency task.