Filters








67 Hits in 6.5 sec

TREC and TIPSTER experiments with inquery

James P Callan, W.Bruce Croft, John Broglio
1995 Information Processing & Management  
This paper describes recent improvements to the system as a result of participation in the TIPSTER project and the TREC-2 conference.  ...  INQUERY is a probablistic information retrieval system based upon a Bayesian inference network model.  ...  This research was partially supported by the NSF Center for Intelligent Information Retrieval at the University of Massachusetts, Amherst.  ... 
doi:10.1016/0306-4573(94)00050-d fatcat:byry5vcvfbgetpxvzyfjc7z6oy

Autonomy and Reliability of Continuous Active Learning for Technology-Assisted Review [article]

Gordon V. Cormack, Maura R. Grossman
2015 arXiv   pre-print
from four separate sets of tasks: the legal datasets examined by Cormack and Grossman, the Reuters RCV1-v2 subject categories, the TREC 6 AdHoc task, and the construction of the TREC 2002 filtering test  ...  and reviewed, using relevance feedback, until substantially all of the relevant documents have been reviewed.  ...  For each of 100 candidate topics, ad hoc search was used to retrieve and label 100 potentially relevant documents.  ... 
arXiv:1504.06868v1 fatcat:vg344hhgxvcphpfqwpwwcn3iiq

Least Information Modeling for Information Retrieval [article]

Weimao Ke
2012 arXiv   pre-print
Experiments on four benchmark TREC collections for ad hoc retrieval showed that LIT-based methods demonstrated very strong performances compared to classic TF*IDF and BM25, especially for verbose queries  ...  We observed several important characteristics of the proposed theory and derived two quantities in the IR context for document representation.  ...  These data had been widely used in TREC for ad hoc retrieval experiments.  ... 
arXiv:1205.0312v1 fatcat:icdmnxx65faavkaoycgiqziznm

On the history of evaluation in IR

Stephen Robertson
2008 Journal of information science  
It describes some of the early experiments that were formative in our understanding, and goes on to discuss the current dominance of TREC (the Text REtrieval Conference) and to assess its impact.  ...  This paper is a personal take on the history of evaluation experiments in information retrieval.  ...  Acknowledgements I am grateful to the following for extremely useful comments on drafts of this paper: Alan Gilchrist, Donna Harman, Ellen Voorhees, Chris Buckley, Bob Oddy, and an anonymous referee.  ... 
doi:10.1177/0165551507086989 fatcat:ecoenm7f3zb3zeap5quurut3ka

Test Collection Based Evaluation of Information Retrieval Systems

Mark Sanderson
2010 Foundations and Trends in Information Retrieval  
Use of test collections and evaluation measures to assess the effectiveness of information retrieval systems has its origins in work dating back to the early 1950s.  ...  This monograph surveys the research conducted and explains the methods and measures devised for evaluation of retrieval systems, including a detailed look at the use of statistical significance testing  ...  many of the measures used by the IR community. 3 The Other TREC Tracks and Uses of TREC Collections Although the test collections and other associated data resulting from TREC ad hoc is the strongest  ... 
doi:10.1561/1500000009 fatcat:qdacqkqj25eojkpchctdzvrt2e

The weighted Condorcet fusion in information retrieval

Shengli Wu
2013 Information Processing & Management  
Section 5 presents the settings and methodologies used for the experiment.  ...  The Condorcet fusion is a distinctive fusion method and was found useful in information retrieval.  ...  TREC 8, the smallest data set among the three of them, is used in this experiment.  ... 
doi:10.1016/j.ipm.2012.02.007 fatcat:ajgvj35sirecblg6nzayo7eani

Modeling and solving term mismatch for full-text retrieval

Le Zhao
2012 SIGIR Forum  
Even though modern retrieval systems typically use a multitude of features to rank documents, the backbone for search ranking is usually the standard tf.idf retrieval models.  ...  Even though the term recall probability is known to be a fundamental quantity in the theory of probabilistic information retrieval, prior research in ad hoc retrieval provided few clues about how to estimate  ...  . 3 3: Term recall (P (t|R)) of 5 example terms (stemmed) on 5 sample queries from TREC 3 title queries.Query (TREC 3 Ad Hoc Retrieval Track)Term P (t|R) idf School Choice Voucher System and its effects  ... 
doi:10.1145/2422256.2422277 fatcat:iboh56u5kvdrhcnt4uqyorwvp4

Topic Models Ensembles for AD-HOC Information Retrieval

Pablo Ormeño, Marcelo Mendoza, Carlos Valle
2021 Information  
Ad hoc information retrieval (ad hoc IR) is a challenging task consisting of ranking text documents for bag-of-words (BOW) queries.  ...  Classic approaches based on query and document text vectors use term-weighting functions to rank the documents.  ...  Data Availability Statement: The datasets used in this study areavailable in: http://ir.dcs.gla.ac.uk/ resources/test_collections/ accessed on 1 March 2021.  ... 
doi:10.3390/info12090360 fatcat:l3zy7twjgrgyjc7fqixynafo34

Probabilistic combination of text classifiers using reliability indicators

Paul N. Bennett, Susan T. Dumais, Eric Horvitz
2002 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02  
We provide background, present procedures for building metaclassifiers that take into consideration both reliability indicators and classifier outputs, and review a set of comparative studies undertaken  ...  to evaluate the methodology.  ...  Acknowledgments We thank Max Chickering and Robert Rounthwaite for their special support of the WinMine toolkit, and John Platt for advice and code support for the linear SVM classifier.  ... 
doi:10.1145/564410.564413 fatcat:ljpquf4zh5c53jv473rlvuvp3i

Probabilistic combination of text classifiers using reliability indicators

Paul N. Bennett, Susan T. Dumais, Eric Horvitz
2002 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02  
We provide background, present procedures for building metaclassifiers that take into consideration both reliability indicators and classifier outputs, and review a set of comparative studies undertaken  ...  to evaluate the methodology.  ...  Acknowledgments We thank Max Chickering and Robert Rounthwaite for their special support of the WinMine toolkit, and John Platt for advice and code support for the linear SVM classifier.  ... 
doi:10.1145/564376.564413 dblp:conf/sigir/BennettDH02 fatcat:37eie2re2nfy3ozf54ifwifiwe

Classification-based Retrieval Methods to Enhance Information Discovery on the Web

Yogendra Kumar Jain, Sandeep Wadekar
2011 International Journal of Managing Information Technology  
The ongoing struggle of information retrieval systems is to wade through this vast pile of data and satisfy users by presenting them with information that most adequately it's their needs.  ...  The widespread adoption of the World-Wide Web (the Web) has created challenges both for society as a whole and for the technology used to build and maintain the Web.  ...  This task is exemplified by the early TREC conferences, where the ad-hoc document retrieval track was prominent [2] .  ... 
doi:10.5121/ijmit.2011.3103 fatcat:vegjt3nfc5cyhivyxw3r2nt4li

The Combination of Text Classifiers Using Reliability Indicators

Paul N. Bennett, Susan T. Dumais, Eric Horvitz
2005 Information retrieval (Boston)  
We provide background, present procedures for building metaclassifiers that take into consideration both reliability indicators and classifier outputs, and review a set of comparative studies undertaken  ...  to evaluate the methodology.  ...  We would also like to thank the anonymous reviewers for the useful suggestions they provided.  ... 
doi:10.1023/b:inrt.0000048491.59134.94 fatcat:npam43vx5fbjtmq775gpjw54c4

On the Estimation and Use of Statistical Modelling in Information Retrieval [article]

Casper Petersen
2019 arXiv   pre-print
Overall, this thesis concludes that distributional assumptions can be replaced with an effective, efficient and principled method for determining the "true" distribution and that using the "true" distribution  ...  Several tasks in information retrieval (IR) rely on assumptions regarding the distribution of some property (such as term frequency) in the data being processed.  ...  Acknowledgements I am deeply indebted to my two supervisors Christina Lioma and Jakob Grue Simonsen for the patience and guidance they have offered me during the past three years.  ... 
arXiv:1904.00289v1 fatcat:a454xqytbjdjbiobuhl4cuzh5u

An evaluation of adaptive filtering in the context of realistic task-based information exploration

Daqing He, Peter Brusilovsky, Jaewook Ahn, Jonathan Grady, Rosta Farzan, Yefei Peng, Yiming Yang, Monica Rogati
2008 Information Processing & Management  
This study is a successful use case of the framework, and the study indeed revealed various aspects of the information systems and their roles in supporting task-based information exploration.  ...  It views the user rather than the information system as the center of the evaluation, and examines how well users are served by the systems in their tasks.  ...  Shulman and his QDAP center for their help in developing the ground truth annotations. Thank Qi Li and Jongdo Park for helping in results analyses.  ... 
doi:10.1016/j.ipm.2007.07.009 fatcat:xwevvzbchvabjogsk73zsv6rvu

A Semantic Searching Scheme in Heterogeneous Unstructured P2P Networks

Jun-Cheng Huang, Xiu-Qi Li, Jie Wu
2011 Journal of Computer Science and Technology  
Our simulation using the IR benchmark TREC collection demonstrates that CSS outperforms GES in terms of higher recall, higher precision, and lower search cost.  ...  ., employ search models in Information Retrieval (IR). All these IR-based schemes use one vector to summarize semantic contents of all documents on a single node.  ...  Text Datasets We use all documents of AP newswire 1988 along with Topics 151∼200 in TREC disks 1&2 to evaluate our search scheme. They can be found in TREC's ad hoc test collections [39] .  ... 
doi:10.1007/s11390-011-1190-z fatcat:oxy3magcunepnoiujg6ixpm6ta
« Previous Showing results 1 — 15 out of 67 results