LINGUIST List 14.981

Wed Apr 2 2003

Books: Modified Issue 14.941: Pasca

Editor for this issue: Marisa Ferrara <marisalinguistlist.org>

Directory

1. sosa, Open-Domain Question Answering from Large Text Collections

			
Title: Open-Domain Question Answering from Large Text Collections
Series Title: CSLI Studies in Computational Linguistics
			
Publication Year: 2003
Publisher: CSLI Publications
 http://csli-publications.stanford.edu/
			
Availability: Available
 
Author: Marius Pasca, Language Computer Corporation 

Hardback: ISBN: 1575864274, Pages: 162, Price: 70.00
Paperback: ISBN: 1575864282, Pages: 162, Price: 25.00
			
Abstract:
			
Vast amounts of information--from newspapers, journals, legal
transcripts, conference proceedings, correspondence, web pages, and
other sources--have become increasingly accessible online. Yet
current keyword-based search technologies offer little support to
users searching for a few relevant text fragments among thousands of
documents.

Open-domain question answering has recently emerged as a new field
aimed at the extraction of brief, relevant answers from large text
collections in response to written questions submitted by
users. Individual related fields--such as natural language processing
or information retrieval--do not allow for practicable solutions to
open-domain question answering. For example, document retrieval alone
is insufficient because relevant information is concentrated in
document fragments that are small when compared to the size of the
entire document. Advanced methods based on higher levels of text
understanding cannot be applied directly to gigabyte-sized collections
of unrestricted text. Similarly, the amount of knowledge required by
an open-domain question answering system to act as an intelligent
conversational agent is beyond the boundaries of present technologies.

This book presents the design of novel and robust methods for
capturing the semantics of natural language questions and for finding
relevant text snippets. The theoretical contributions of this research
are reflected in a fully implemented architecture whose performance
was evaluated within the DARPA-sponsored Text REtrieval Conference. In
addition, experimental results show significant qualitative
improvements with respect to the output from web search engines,
revealing both the challenges and desired features of next-generation
web search technologies.

To order this book, contact: 

The University of Chicago Press. 
Call their toll free order number 1-800-621-2736 (U.S. & Canada only)
or order online at http://www.press.uchicago.edu/ (use the search
feature to locate the book, then order).
			
Lingfield(s): Computational Linguistics

Written In: English (Language Code: English)

 See this book announcement on our website:
	 http://linguistlist.org/get-book.html?BookID=5741