TREC: Experiment and Evaluation in Information Retrieval

Front Cover
E. Voorhees, Donna K. Harman
Penguin Random House LLC, 2005 - Computers - 462 pages

Results from twelve years of the Text REtrieval Conference (TREC), documenting test collections, evaluation standards, and current best practices.

The Text REtrieval Conference (TREC), a yearly workshop hosted by the US government's National Institute of Standards and Technology, provides the infrastructure necessary for large-scale evaluation of text retrieval methodologies. With the goal of accelerating research in this area, TREC created the first large test collections of full-text documents and standardized retrieval evaluation. The impact has been significant; since TREC's beginning in 1992, retrieval effectiveness has approximately doubled. TREC has built a variety of large test collections, including collections for such specialized retrieval tasks as cross-language retrieval and retrieval of speech. Moreover, TREC has accelerated the transfer of research ideas into commercial systems, as demonstrated in the number of retrieval techniques developed in TREC that are now used in Web search engines.This book provides a comprehensive review of TREC research, summarizing the variety of TREC results, documenting the best practices in experimental information retrieval, and suggesting areas for further research. The first part of the book describes TREC's history, test collections, and retrieval methodology. Next, the book provides "track" reports--describing the evaluations of specific tasks, including routing and filtering, interactive retrieval, and retrieving noisy text. The final part of the book offers perspectives on TREC from such participants as Microsoft Research, University of Massachusetts, Cornell University, University of Waterloo, City University of New York, and IBM. The book will be of interest to researchers in information retrieval and related technologies, including natural language processing.

From inside the book

 

45 pages matching Web engines in this book

Where's the rest of this book?

Results 1-3 of 45

Contents

The Text Retrieval Conference
3
The TREC Test Collections
21
Retrieval System Evaluation
53
Copyright

16 other sections not shown

Common terms and phrases

ACM SIGIR conference adaptive filtering algorithms Allan annual international ACM approach assessors automatic average precision bigrams Buckley C. J. van Rijsbergen Chinese CIIR CLIR Computer contained corpus cross-language cross-language information retrieval cross-lingual disks docu document collection document retrieval English error rate evaluation measures example experimental experiments filtering track gigabytes groups Harman hoc retrieval hoc task improvement indexing information retrieval INQUERY interactive track international ACM SIGIR judged language model manual mean reciprocal rank ments methods monolingual n-grams NIST number of relevant Okapi percent performance phrases PIRCS probabilistic Proceedings query expansion query terms question answering ranking recall relevance feedback relevance judgments relevant documents retrieval systems Robertson routing task runs search engine searchers SMART Sparck Jones statistical techniques test collections test set text retrieval conference tion translation TREC TREC ad hoc trieval types University Voorhees W. B. Croft Web engines weighting words

Bibliographic information

TitleTREC: Experiment and Evaluation in Information Retrieval
Digital Libraries and Electron
Digital libraries and electronic publishing
EditorsE. Voorhees, Donna K. Harman
ContributorNational Institute of Standards and Technology (U.S.)
Editionillustrated
PublisherPenguin Random House LLC, 2005
Original fromthe University of Michigan
DigitizedJul 30, 2009
ISBN0262220733, 9780262220736
Length462 pages
Subjects ›  › 

Computers / System Administration / Storage & Retrieval
Language Arts & Disciplines / Library & Information Science / General
  
Export CitationBiBTeX EndNote RefMan