Hybrid long-distance functional dependency parsing

Institute of Computational Linguistics;English Department;000 Computer science, knowledge & systems;820 English & Old English literatures;410 Linguistics;computational linguistics dependency parsing parser deep-linguistic probabilistic long-distance English formal grammar broad-coverage

Schneider, Gerold

University of Zurich

关键词: Institute of Computational Linguistics;    English Department;    000 Computer science, knowledge & systems;    820 English & Old English literatures;    410 Linguistics;    computational linguistics dependency parsing parser deep-linguistic probabilistic long-distance English formal grammar broad-coverage;   

Others  :  http://www.zora.uzh.ch/id/eprint/7188/2/phd_wrapper9FINALV.pdf

瑞士|英语

来源: Zurich Open Repository and Archive

【 摘 要 】

This thesis proposes a robust, hybrid, deep-syntatic dependency-based parsing architecture and presents its implementation and evaluation. The architecture and the implementation are carefully 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 but at the same time mostly context-free and fast enough for large-scale application to unrestricted texts. It combines a number of successful current approaches into a hybrid, comparatively simple, modular and open model. This thesis reports three results: 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 show that inherently complex linguistic problems can be broken down and approximated sufficiently well by less complex methods. In particular (1) on the level of long-distance dependencies, the majority of them can be approximated by using a labelled DG, context-free finite-state based patterns, and post-processing, (2) on the level of long-distance dependencies, a slightly extended DG allows us to use mildly context-sensitive operations known from Tree-Adjoining Grammar (TAG), (3) on the base phrase level, parsing can successfully be approximated by the more shallow approaches of chunking and tagging. We conclude that labelled DG 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.