Graph Transformations in Data-Driven Dependency Parsing

• 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-of-the-art accuracy for the given data set.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Dependency Parsing

Graph Transformation

Computer science

Datalogi

Computer and Information Sciences Computer Science

Data- och informationsvetenskap

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)