We discuss how the scope of speculation and negation can be resolved by learning a ranking function that operates over syntactic constituent subtrees. An important assumption of this method is that scope aligns with constituents, and hence we investigate instances of disalignment. We also show how the method can be combined with an existing scope-resolution system based on manually-crafted rules over dependency structures. While both systems achieve encouraging results, combining the two improves performance beyond either in isolation. Furthermore, coupling this hybrid scope approach with an SVM cue classifier achieves the best published results on data from the CoNLL-2010 Shared Task. 1

I would like to thank Prof. Dr. Lothar Thiele and Dr. Beat Pfister for supervising

This thesis will focus on the feasibility of precision-oriented parsing in the framework of Head-driven Phrase Structure Grammar (Pollard and Sag 1994). Such parsers, traditionally based on hand-written grammars, offer detailed semantic analyses of the language. However, there are a number of barriers that need to be overcome before such a parser can be successfully deployed, most notably the grammar’s long development time. Statistical parsers are less prone to this issue, but do not offer the same depth of analysis that hand-written deep grammars can. A number of approaches (in different linguistic formalisms, often highly lexicalised) have been proposed that aim to combine the advantages of both types of parsers, usually by converting/enriching an existing treebank to a deeper linguistic formalism, after which a deep grammar can be learnt from the richer resource of annotated data. This thesis has a comparable aim, but approaches the problem from the perspective of precision-oriented parsing, automating as much as possible, and crafting by hand what is necessary, for instance because it is not learnable from the available resources. The German language is taken as object of study.