Page 1 |
Save page Remove page | Previous | 1 of 231 | Next |
|
small (250x250 max)
medium (500x500 max)
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
Subset |
WEIGHTED TREE AUTOMATA AND TRANSDUCERS
FOR SYNTACTIC NATURAL LANGUAGE PROCESSING
by
Jonathan David Louis May
A Dissertation Presented to the
FACULTY OF THE USC GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(COMPUTER SCIENCE)
August 2010
Copyright 2010 Jonathan David Louis May
Object Description
| Title | Weighted tree automata and transducers for syntactic natural language processing |
| Author | May, Jonathan David Louis |
| Author email | uscthesis@jonmay.net; jonmay@isi.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2010-04-20 |
| Date submitted | 2010 |
| Restricted until | Unrestricted |
| Date published | 2010-05-28 |
| Advisor (committee chair) | Knight, Kevin |
| Advisor (committee member) |
Marcu, Daniel Chiang, David Koenig, Dven Narayanan, Shrikanth Pereira, Fernando |
| Abstract | Weighted finite-state string transducer cascades are a powerful formalism for models of solutions to many natural language processing problems such as speech recognition, transliteration, and translation. Researchers often directly employ these formalisms to build their systems by using toolkits that provide fundamental algorithms for transducer cascade manipulation, combination, and inference. However, extant transducer toolkits are poorly suited to current research in NLP that makes use of syntax-rich models. More advanced toolkits, particularly those that allow the manipulation, combination, and inference of weighted extended top-down tree transducers, do not exist. In large part, this is because the analogous algorithms needed to perform these operations have not been defined. This thesis solves both these problems, by describing and developing algorithms, by producing an implementation of a functional weighted tree transducer toolkit that uses these algorithms, and by demonstrating the performance and utility of these algorithms in multiple empirical experiments on machine translation data. |
| Keyword | computational linguistics; natural language processing; machine translation; parsing; tree automata; tree transducers; context-free grammars; finite state machines; machine learning |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Provenance | Electronically uploaded by the author |
| Type | texts |
| Legacy record ID | usctheses-m3104 |
| Rights | May, Jonathan David Louis |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | http://www.usc.edu/isd/libraries/services/ask_a_librarian/email/ |
| Filename | etd-May-3726 |
| Archival file | uscthesesreloadpub_Volume14/etd-May-3726.pdf |
Description
| Title | Page 1 |
| Full text | WEIGHTED TREE AUTOMATA AND TRANSDUCERS FOR SYNTACTIC NATURAL LANGUAGE PROCESSING by Jonathan David Louis May A Dissertation Presented to the FACULTY OF THE USC GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) August 2010 Copyright 2010 Jonathan David Louis May |
Comments
Post a Comment for Page 1
