Hybrid Long-Distance Functional Dependency Parsing

We propose a robust, hybrid, deep-syntactic dependency-based parser and present its implementation and evaluation. The parser is designed to keep search-spaces small without compromising much on the linguistic performance or adequacy. The resulting parser is deep-syntactic like a formal grammar-based parser while mostly context-free and fast enough for large-scale application. It combines successful current approaches into a hybrid, modular and open model. We suggest, implement, and evaluate a parsing architecture that is fast, robust and efficient enough to allow users to do broad-coverage parsing of unrestricted texts from varied domains. We present a probability model and a combination between a rule-based competence grammar and a statistical lexicalized performance disambiguation model. We treat long-distance dependencies with post-processing and mild context-sensitivity. We conclude that labelled Dependency Grammar is sufficiently expressive for linguistically adequate parsing. We argue that our parser covers the middle ground between statistical parsing and formal grammar-based parsing. The parser has competitive performance and has been applied widely.

Autorentext

Dr. Gerold Schneider has studied English and ComputationalLinguistics. He took his doctoral degree in 2008, at University of Zurich. He wasassistant in Geneva and is now computing scientist and corpus linguist at the EnglishDepartment of the University of Zurich. His research includes Natural LanguageProcessing and Descriptive Linguistics.