Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Transforming syntactic representations in order to improve parsing accuracy has been exploited successfully in statistical parsing systems using constituency-based representations. In this paper, we show that similar transformations can give substantial improvements also in data-driven dependency parsing. Experiments on the Prague Dependency Treebank show that systematic transformations of coordinate structures and verb groups result in a 10% error reduction for a deterministic data-driven dependency parser. Combining these transformations with previously proposed techniques for recovering nonprojective dependencies leads to state-ofthe-art accuracy for the given data set. . | Graph Transformations in Data-Driven Dependency Parsing Jens Nilsson Vaxjo University j ni@msi.vxu.se Joakim Nivre Vaxjo University and Uppsala University nivre@msi.vxu.se Johan Hall Vaxjo University j ha@msi.vxu.se Abstract Transforming syntactic representations in order to improve parsing accuracy has been exploited successfully in statistical parsing systems using constituency-based representations. In this paper we show that similar transformations can give substantial improvements also in data-driven dependency parsing. Experiments on the Prague Dependency Treebank show that systematic transformations of coordinate structures and verb groups result in a 10 error reduction for a deterministic data-driven dependency parser. Combining these transformations with previously proposed techniques for recovering non-projective dependencies leads to state-of-the-art accuracy for the given data set. 1 Introduction It has become increasingly clear that the choice of suitable internal representations can be a very important factor in data-driven approaches to syntactic parsing and that accuracy can often be improved by internal transformations of a given kind of representation. This is well illustrated by the Collins parser Collins 1997 Collins 1999 scrutinized by Bikel 2004 where several transformations are applied in order to improve the analysis of noun phrases coordination and punctuation. Other examples can be found in the work of Johnson 1998 and Klein and Manning 2003 which show that well-chosen transformations of syntactic representations can greatly improve the parsing accuracy obtained with probabilistic context-free grammars. In this paper we apply essentially the same techniques to data-driven dependency parsing specifically targeting the analysis of coordination and verb groups two very common constructions that pose special problems for dependency-based approaches. The basic idea is that we can facilitate learning by transforming the training data for the .
