Skip Nav Destination
Close Modal
Update search
NARROW
Format
Subjects
Date
Availability
1-20 of 25
Daniel Marcu
Close
Follow your search
Access your saved searches in your account
Would you like to receive an alert when new items match your search?
Sort by
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.001.0001
EISBN: 9780262316095
This book documents the first serious attempt to construct automatically and use nonsemantic computational structures for text summarization. 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.
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0011
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0013
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0014
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0015
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0016
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0018
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0019
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0020
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0021
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0022
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0023
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0024
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0001
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0002
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0003
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0004
EISBN: 9780262316095
Publisher: The MIT Press
Published: 08 November 2000
DOI: 10.7551/mitpress/6754.003.0005
EISBN: 9780262316095