tailieunhanh - Báo cáo khoa học: "Generalizing Tree Transformations for Inductive Dependency Parsing"

Previous studies in data-driven dependency parsing have shown that tree transformations can improve parsing accuracy for specific parsers and data sets. We investigate to what extent this can be generalized across languages/treebanks and parsers, focusing on pseudo-projective parsing, as a way of capturing non-projective dependencies, and transformations used to facilitate parsing of coordinate structures and verb groups. | Generalizing Tree Transformations for Inductive Dependency Parsing Jens Nilsson Joakim Nivre Johan Hall Vaxjo University School of Mathematics and Systems Engineering Sweden Uppsala University Dept. of Linguistics and Philology Sweden jni nivre jha @ Abstract Previous studies in data-driven dependency parsing have shown that tree transformations can improve parsing accuracy for specific parsers and data sets. We investigate to what extent this can be generalized across languages treebanks and parsers focusing on pseudo-projective parsing as a way of capturing non-projective dependencies and transformations used to facilitate parsing of coordinate structures and verb groups. The results indicate that the beneficial effect of pseudo-projective parsing is independent of parsing strategy but sensitive to language or treebank specific properties. By contrast the construction specific transformations appear to be more sensitive to parsing strategy but have a constant positive effect over several languages. 1 Introduction Treebank parsers are trained on syntactically annotated sentences and a major part of their success can be attributed to extensive manipulations of the training data as well as the output of the parser usually in the form of various tree transformations. This can be seen in state-of-the-art constituency-based parsers such as Collins 1999 Charniak 2000 and Petrov et al. 2006 and the effects of different transformations have been studied by Johnson 1998 Klein and Manning 2003 and Bikel 2004 . Corresponding manipulations in the form of tree transformations for dependency-based parsers have recently 968 gained more interest Nivre and Nilsson 2005 Hall and Novak 2005 McDonald and Pereira 2006 Nilsson et al. 2006 but are still less studied partly because constituency-based parsing has dominated the field for a long time and partly because dependency structures have less structure to manipulate than constituent structures. Most of the studies in this