tailieunhanh - Báo cáo khoa học: "Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures"

Dependency analysis of natural language has gained importance for its applicability to NLP tasks. 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. . | Beyond Projectivity Multilingual Evaluation of Constraints and Measures on Non-Projective Structures Jin Havelka Institute of Formal and Applied Linguistics Charles University in Prague Czech Republic havelka@ Abstract Dependency analysis of natural language has gained importance for its applicability to NLP tasks. 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. 1 Introduction Dependency analysis of natural language has been gaining an ever increasing interest thanks to its applicability in many tasks of NLP a recent example is the dependency parsing work of McDonald et al. 2005 which introduces an approach based on the search for maximum spanning trees capable of handling non-projective structures naturally. The study of dependency structures occurring in natural language can be approached from two sides 608 by trying to delimit permissible dependency structures through formal constraints for a recent review paper see Kuhlmann and Nivre 2006 or by providing their linguistic description see . Vesela et al. 2004 and Hajicova et al. 2004 for a linguistic analysis of non-projective constructions in We think that it is worth bearing in mind that neither syntactic structures in dependency treebanks nor structures