Dissertation/Thesis Abstract

Scalable graph -based learning applied to human language technology
by Alexandrescu, Andrei, Ph.D., University of Washington, 2009, 206; 3377339
Abstract (Summary)

Graph-based semi-supervised learning techniques have recently attracted increasing attention as a means to utilize unlabeled data in machine learning by placing data points in a similarity graph. However, applying graph-based semi-supervised learning to natural language processing tasks presents unique challenges. First, natural language features are often discrete and do not readily reveal an underlying manifold structure, which complicates the already empirical graph construction process. Second, natural language processing problems often use structured inputs and outputs that do not naturally fit the graph-based framework Finally, scalability issues limit applicability to large data sets, which are common even in modestly-sized natural language processing applications. This research investigates novel approaches to using graph-based semi-supervised learning techniques for natural language processing, and addresses issues of distance measure learning, scalability, and structured inputs and outputs.

Indexing (document details)
Advisor: Kirchhoff, Katrin
School: University of Washington
School Location: United States -- Washington
Source: DAI-B 70/09, Dissertation Abstracts International
Subjects: Computer science
Keywords: Graph-based learning, Machine learning, Natural language processing
Publication Number: 3377339
ISBN: 978-1-109-39581-5
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy