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.
Daniel Marcu is Director of Strategic Initiatives at the Information Sciences Institute and Research Associate Professor in the Department of Computer Science at the University of Southern California.
"Sobre este título" puede pertenecer a otra edición de este libro.
EUR 35,74 gastos de envío desde Estados Unidos de America a España
Destinos, gastos y plazos de envíoEUR 11,89 gastos de envío desde Reino Unido a España
Destinos, gastos y plazos de envíoLibrería: Dorley House Books, Inc., Hagerstown, MD, Estados Unidos de America
Hardcover. Condición: Near Fine. Estado de la sobrecubierta: Near Fine. 1st. 1st printing; dj in mylar; blue c w/gilt spine titles; 272 clean, unmarked pages. Nº de ref. del artículo: 116271
Cantidad disponible: 1 disponibles
Librería: PAPER CAVALIER UK, London, Reino Unido
Condición: new. New! Nº de ref. del artículo: 9780262133722-1
Cantidad disponible: 1 disponibles
Librería: Toscana Books, AUSTIN, TX, Estados Unidos de America
Hardcover. Condición: new. Excellent Condition.Excels in customer satisfaction, prompt replies, and quality checks. Nº de ref. del artículo: Scanned0262133725
Cantidad disponible: 1 disponibles
Librería: HPB-Red, Dallas, TX, Estados Unidos de America
Hardcover. Condición: Good. Connecting readers with great books since 1972! Used textbooks may not include companion materials such as access codes, etc. May have some wear or writing/highlighting. We ship orders daily and Customer Service is our top priority! Nº de ref. del artículo: S_330282587
Cantidad disponible: 1 disponibles