Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures
Abstract
Dependency analysis of natural language has gained importance for its applicability in tasks of NLP. Non-projective structures are common in dependency analysis, therefore we need fine-grained means of describing them, especially for the purposes of machine-learning oriented approaches like parsing.
We present an evaluation on twelve languages which explores several constraints and measures on non-projective structures. We pursue an edge-based approach concentrating on properties of individual edges as opposed to properties of whole trees.
In our evaluation, we include previously unreported measures taking into account levels of nodes in dependency trees. Our empirical results corroborate theoretical results and show that an edge-based approach using levels of nodes provides an accurate and at the same time expressive means for capturing non-projective structures in natural language.