Permanent URL to this publication: http://dx.doi.org/10.5167/uzh-7188
Schneider, G. Hybrid long-distance functional dependency parsing. 2008, University of Zurich, Faculty of Arts.
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.
|Referees:||Hess M, Merlo P|
|Communities & Collections:||06 Faculty of Arts > Institute of Computational Linguistics|
06 Faculty of Arts > Institute of English Studies
|DDC:||000 Computer science, knowledge & systems|
820 English & Old English literatures
|Uncontrolled Keywords:||computational linguistics dependency parsing parser deep-linguistic probabilistic long-distance English formal grammar broad-coverage|
|Deposited On:||18 Dec 2008 10:24|
|Last Modified:||09 Jul 2012 05:28|
|Number of Pages:||274|
|Funders:||Swiss National Science Fund|
|Related URLs:||http://www.cl.uzh.ch/CL/gschneid/ (Author)|
Users (please log in): suggest update or correction for this item
Repository Staff Only: item control page