Deterministic dependency parsing of unrestricted English text

Nedanstående innehåll är skapat av Mimers Brunns besökare. Kommentera arbete

This master’s thesis describes a deterministic dependency parser using a memorybasedlearning approach to parse unrestricted English text. A converter transformsthe Wall Street Journal section of the Penn Treebank to an intermediate dependencyrepresentation which is used to train the parser using the TiMBL (Daelemans, Zavrel,Sloot, & Bosch, 2003) library. The output of the parser is labeled dependency graphs,using as arc labels a combination of bracket labels and grammatical role labels constructedfrom the Penn Treebank II annotation scheme (Marcus, Kim, et al., 1994). Theparser reaches a maximum unlabeled attachment score of 87.1% and produces labeleddependency graphs with an accuracy of of 86.0% with the correct head and arc labelrecognised. The results are close to the state of the art in dep...