Does it have to be trees? : Data-driven dependency parsing with incomplete and noisy training data [Elektronische Ressource] / Kathrin Spreyer. Betreuer: Jonas Kuhn

Does It Have To Be Trees?Data-Driven Dependency Parsing withIncomplete and Noisy Training DataDissertation von Kathrin SpreyerEingereicht bei der Humanwissenschaftlichen Fakulta¨tder Universita¨t Potsdamzur Erlangung des Grades des Doktors der PhilosophieHeidelberg, 11. Oktober 2011 This work is licensed under a Creative Commons License: Attribution - Noncommercial - Share Alike 3.0 Unported To view a copy of this license visit http://creativecommons.org/licenses/by-nc-sa/3.0/ Gutachter: Prof. Dr. Jonas Kuhn Prof. Dr. Manfred Stede Datum der mündlichen Prüfung: 15. Dezember 2011 The research that led to this dissertation was funded by the DFG as part of the collaborative research center SFB 632. Published online at the Institutional Repository of the University of Potsdam: URL http://opus.kobv.de/ubp/volltexte/2012/5749/ URN urn:nbn:de:kobv:517-opus-57498 http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-57498 iiiErklarung¨Ich erklare, dass ich diese Dissertation selbstandig verfasst und keine anderen¨ ¨als die angegebenen Quellen und Hilfsmittel verwendet habe.Heidelberg, den 11. Oktober 2011.Kathrin SpreyerivAbstractWe present a novel approach to training data-driven dependency parsers on in-complete annotations. Our parsers are simple modifications of two well-knowndependencyparsers, thetransition-basedMaltparserandthegraph-basedMSTparser.