Publications: Discourse Parsing and Summarization

alexis nasr alexis.nasr at
Tue Mar 13 19:06:51 UTC 2001

The Theory and Practice of Discourse Parsing and Summarization
Daniel Marcu

Until now, most discourse researchers have assumed that full semantic
understanding is necessary to derive the discourse structure of texts. This
book documents the first serious attempt to construct automatically and use
nonsemantic computational structures for text summarization. Daniel Marcu
develops a semantics-free theoretical framework that is both general enough
to be applicable to naturally occurring texts and concise enough to
facilitate an algorithmic approach to discourse analysis. He presents and
evaluates two discourse parsing methods: one uses manually written rules
that reflect common patterns of usage of cue phrases such as "however" and
"in addition to"; the other uses rules that are learned automatically from
a corpus of discourse structures. By means of a psycholinguistic
experiment, Marcu demonstrates how a discourse-based summarizer identifies
the most important parts of texts at levels of performance that are close
to those of humans.

Marcu also discusses how the automatic derivation of discourse structures
may be used to improve the performance of current natural language
generation, machine translation, summarization, question answering, and
information retrieval systems.

Daniel Marcu is a Research Scientist at the Information Sciences Institute
at the University of Southern California and Research Assistant Professor
in the university's Department of Computer Science.

7 x 9, 272 pp., 68 illus., cloth ISBN 0-262-13372-5
A Bradford Book

Message diffusé par la liste Langage Naturel <LN at>
Informations, abonnement :
English version          :
Archives                 :

More information about the Ln mailing list