Statistical parsing for German: modeling syntactic properties and annotation differences

Statistical parsing research can be described as being anglo-centric: new models are first proposed for English parsing, and only then tested in other languages. Indeed, a standard approach to parsing with new treebanks is to adapt fully developed English parsing models to the other language. In this dissertation, however, we claim that many assumptions of English parsing do not generalize to other languages and treebanks because of linguistic and annotation differences. For example, we show that lexicalized models originally proposed for English parsing generalize poorly to German. Even after modifying the models to account for annotation differences, we find the benefit of lexicalization to be far less than in English. With this as a starting point, we take a closer look what effect that linguistic differences between English and German have on statistical parsing results. We find that a number of linguistic elements of German play a more crucial role than lexicalization. For example, adding a relatively simple model of the German case system to parser accounts for more ambiguity than a complex model including lexicalization. Further studies show that lexical category ambiguity accounts for a surprising amount of parsing mistakes, and while a model of morphology we develop gives mixed results, an error analysis suggets that a correct model of morphology would help with resolving harmful and common verb/adjective ambiguities. In addition, we offer a preliminary model of long-distance dependencies, showing this model helps greatly in resolving ambiguities caused by German free word order constructions. We also find that the choice of evaluation metric can have a profound impact on parsing performance: it appears that lexicalized models perform better on dependency-based metrics whereas unlexicalized models perform better on labelled bracketing metrics. Other seemingly arbitrary choices also affect parsing results: the choice of search and smoothing algorithm can potentially obscure helpful linguistic disambiguation cues. The best performing model we develop sets the state-of-the-art performance on the NEGRA and TIGER corpora, with labelled bracketing scores of 76.2 on NEGRA and 79.5 on TIGER. Furthermore, this parser scores 84.0 on dependencies on the NEGRA corpus, also the best reported performance on that corpus, and 86.2 on the TIGER corpus.