文档介绍：This page intentionally left blank
GRAPH-BASED NATURAL LANGUAGE PROCESSING
AND INFORMATION RETRIEVAL
Graph theory and the fields of natural language processing and information
retrieval are well-studied disciplines. Traditionally, these areas have been per-
ceived as distinct, with different algorithms, different applications, and different
potential end-users. However, recent research has shown that these disciplines
are intimately connected, with much variety in the way that natural language
processing and information retrieval applications find efficient solutions within
graph-theoretical frameworks.
This book is prehensive description of the use of graph-based algo-
rithms for natural language processing and information retrieval. It brings
together topics as diverse as lexical semantics, text summarization, text min-
ing, ontology construction, text classification, and text retrieval, which are
connected by mon underlying theme of the use of graph-theoretical
methods for text- and information-processing tasks. Readers will gain a firm
understanding of the major methods and applications in natural language pro-
cessing and information retrieval that rely on graph-based representations and
algorithms.
Rada Mihalcea is an Associate Professor in the Department puter Sci-
ence and Engineering at the University of North Texas, where she leads the
Language and Information Technologies research group. In 2009, she received
the Presidential Early Career Award for Scientists and Engineers, awarded by
President Barack Obama. She served on the editorial board of several journals,
putational Linguistics, Journal of Natural Language Engineer-
ing, and Language Resources and Evaluations, and she cochaired the Empirical
Methods in Natural Language Processing Conference in 2009 and the Associa-
tion putational Linguistics Conference in 2011. She has been published
in IEEE Intelligent Systems, Journal of Natural Language Engineering, Jour-
nal of Machin