A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
IIT at TREC-8: Improving Baseline Precision
1999
Text Retrieval Conference
This year, we focussed on improving our baseline and then introduced some experimental improvements. ...
In TREC-8, we participated in the automatic and manual tracks for category A as well as the small web track. ...
Acknowledgments We wish to thank the director and staff at the Major Shared Resource Center, U.S. ...
dblp:conf/trec/McCabeHACGF99
fatcat:phdg62iukjhp7d64wwlwbcskuu
The TREC-2001 Cross-Language Information Retrieval Track: Searching Arabic Using English, French or Arabic Queries
2001
Text Retrieval Conference
On average, forty percent of the relevant documents discovered by a participating team were found by no other team, a higher rate than normally observed at TREC. ...
Acknowledgments We are grateful to Ellen Voorhees for coordinating this track at NIST and for her extensive assistance with our preliminary analysis, to the participating research teams for their advice ...
Stems generated from the same root typically have related meanings, so indexing roots might improve recall (possibly at the expense of precision, though). ...
dblp:conf/trec/GeyO01
fatcat:cwkg2mal3zgrpewhdtyo333tea
MSIR@FIRE: A Comprehensive Report from 2013 to 2016
2020
SN Computer Science
This document is a comprehensive report on the 4 years of MSIR track evaluated at FIRE between 2013 and 2016. ...
MSIR track was first introduced in 2013 at FIRE and the aim of MSIR was to systematically formalize several research problems that one must solve to tackle the code mixing in Web search for users of many ...
The success of TREC, 8 CLEF, 9 and NTCIR 10 has clearly established the importance of an evaluation workshop that facilitates research by providing the data and a common forum for comparing models and ...
doi:10.1007/s42979-019-0058-0
fatcat:z5ojljqkkfatph46hzjj6epnny
Collection statistics for fast duplicate document detection
2002
ACM Transactions on Information Systems
We compared our solution to the state of the art and found that in addition to improved accuracy of detection, our approach executed in roughly one-fifth the time. ...
Seventeen inconsistencies were detected in TREC 8 and 65 inconsistencies were noted for the web track of TREC 8. ...
Similar examples were found for TREC 7 and 8 and the web track of TREC 8. ...
doi:10.1145/506309.506311
fatcat:eilrac57nfgwnagybd3n2jyb2a
Overview of the TREC 2006
2006
Text Retrieval Conference
A similar investigation of the TREC-8 ad hoc collection showed that every automatic run that had a mean average precision score of at least 0.1 had a percentage difference of less than 1 % between the ...
At varying cut-off levels, recall and precision tend to be inversely related since retrieving more documents will usually increase recall while degrading precision and vice versa. ...
dblp:conf/trec/Voorhees06
fatcat:5olfha4lxvcqbahxz7rl6bldha
Query Refinement in Similarity Retrieval Systems
2001
IEEE Data Engineering Bulletin
Experiments with the model for spreading activation In this subsection, we present our experiments done on the CACM and Trec'8 web test-collections. ...
¯It reaches good precision and recall, after few iterations. For instance, with all queries, « yielded at least 80% precision at 50% recall with 10 iterations. ...
He is the current Vice Chair of the IEEE TCDE and the Chair of the ICDE Steering Committee and also a member of the JCDL at ECDL Steering Committees. He is a Senior Member of IEEE.
ELECTION BALLOT ...
dblp:journals/debu/ChakrabartiOPM01
fatcat:kwrajv6a2rbr5kng7lmk66a5wu