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
The Text REtrieval Conferences (TRECs)
1996
Proceedings of a workshop on held at Vienna, Virginia May 6-8, 1996 -
Preserved Fulltext
Thanks also go to the TREC program committee and the staff at NIST. The TREC tracks could not happen without the efforts of the track coordinators; our special thanks to them. ...
Acknowledgments The authors gratefully acknowledge the continued support of the TREC conferences by the Intelligent Systems Office of the Defense Advanced Research Projects Agency. ...
Nine groups submitted Chinese runs in TREC-5, and since it was the first year for Chinese in TREC, most groups concentrated on segmentation issues. ...
doi:10.3115/1119018.1119026
dblp:conf/tipster/Harman96
fatcat:wjklhj3nwnenfkfxben2756yla
The Text REtrieval Conferences (TRECs)
1996
Proceedings of a workshop on held at Vienna, Virginia May 6-8, 1996 -
Preserved Fulltext
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.
Thanks also go to the TREC program committee and the staff at NIST. The TREC tracks could not happen without the efforts of the track coordinators; our special thanks to them. ...
Acknowledgments The authors gratefully acknowledge the continued support of the TREC conferences by the Intelligent Systems Office of the Defense Advanced Research Projects Agency. ...
Nine groups submitted Chinese runs in TREC-5, and since it was the first year for Chinese in TREC, most groups concentrated on segmentation issues. ...
doi:10.3115/1119018.1119070
dblp:conf/tipster/Harman96a
fatcat:bxx2gy23cbeenn5ryxedzg3ixe
The text retrieval conferences (TRECS)
1996
Proceedings of a workshop on held at Baltimore, Maryland October 13-15, 1998 -
Preserved Fulltext
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.
Thanks also go to the TREC program committee and the staff at NIST. The TREC tracks could not happen without the efforts of the track coordinators; our special thanks to them. ...
Acknowledgments The authors gratefully acknowledge the continued support of the TREC conferences by the Intelligent Systems Office of the Defense Advanced Research Projects Agency. ...
Nine groups submitted Chinese runs in TREC-5, and since it was the first year for Chinese in TREC, most groups concentrated on segmentation issues. ...
doi:10.3115/1119089.1119127
dblp:conf/tipster/VoorheesH98
fatcat:yo3fnbp2tffqzfjhndiwd4zsre
The TREC 2002 Filtering Track Report
2002
Text Retrieval Conference
Preserved Fulltext
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.
In adaptive filtering, the system begins with only a topic statement and a small number of positive examples, and must learn a better profile from on-line feedback. ...
The TREC-11 filtering track measures the ability of systems to build persistent user profiles which successfully separate relevant and non-relevant documents in an incoming stream. ...
Acknowledgements We give our thanks to all the people who have contributed to the development of the TREC filtering track over the years, in particular David Lewis, David Hull, Karen Sparck Jones, Chris ...
dblp:conf/trec/RobertsonS02
fatcat:fwhyepunqfgndikadr55ztwbwu
The TREC experiments and their impact on Europe
1997
Journal of information science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
Information retrieval (IR) research on text collections has concentrated on improving the effectiveness of the indexing and retrieval operations. ...
In 1992 the first of a series of evaluation exercises called TREC (Text REtrieval Conference) was launched in the US and these exercises have continued annually since then. ...
In addition to the ad hoc retrieval mode, TREC also runs in parallel, a filtering or routing mode. ...
doi:10.1177/016555159702300208
fatcat:5tionsnxuvcg3fn7wto4rtgyfe
The TREC experiments and their impact on Europe
1997
Journal of information science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
Information retrieval (IR) research on text collections has concentrated on improving the effectiveness of the indexing and retrieval operations. ...
In 1992 the first of a series of evaluation exercises called TREC (Text REtrieval Conference) was launched in the US and these exercises have continued annually since then. ...
In addition to the ad hoc retrieval mode, TREC also runs in parallel, a filtering or routing mode. ...
doi:10.1177/016555159702300302
fatcat:k237c67jznhfjfrnn63bfzgloq
The Development and Evolution of TREC and DUC
2002
NTCIR Conference on Evaluation of Information Access Technologies
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The Text REtrieval Conference (TREC) has been running for 11 years now, with 93 participants in the last round of evaluation. ...
This paper chronicles the changes in TREC over that time, emphasizing the evolution in the tasks that were evaluated rather than discussing the results of the specific evaluations. ...
Starting in TREC-4, a filtering track has worked on the binary version of the routing task, using utility functions as measures of the quality of the retrieved set. ...
dblp:conf/ntcir/Harman02
fatcat:vepvpz66l5arnmp35ktqgebiry
TREC 11 Experiments at CAS-ICT: Filtering and Web
2002
Text Retrieval Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
CAS-ICT took part in the TREC conference for the second time this year and we undertook two tracks of TREC-11. For filtering track, we have submitted results of all three subtasks. ...
In batch filtering and routing, a centroid-based classifier is used with preprocessed samples. For Web track, we have submitted results of both two subtasks. ...
We give our thanks to all the people who have contributed to this research and development, in particular Yanbo Han, Li Guo, Qun Liu, Xin Zhang, Hao Zhang, Dongbo Bu and Huaping Zhang. ...
dblp:conf/trec/XuYWLCLYCB02
fatcat:exdpqntcjbbt5pmlkcahqyiz3q
Building Better Search Engines by Measuring Search Quality
2014
IT Professional Magazine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The NIST Text REtrieval Conference (TREC) project has been instrumental in creating the necessary infrastructure to measure the quality of search results for more than twenty years, and has thus helped ...
on the actions recorded in the clip rather than file names and donor tags. ...
Filtering The ad hoc task and a routing task were the only two tasks in the first years of TREC. ...
doi:10.1109/mitp.2013.105
fatcat:hk3zocjbxjawhfuye4k7gkcvqq
Further reflections on TREC
2000
Information Processing & Management
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2003; you can also visit the original URL.
The file type is application/pdf.
One implication is that TREC should move into a new phase targeted on key comparisons and task speci®cations designed to deliver substantive new information, in particular shifting towards situated IR ...
The paper focuses on the ad hoc retrieval task, with discussion of other test tracks as appropriate. ...
Acknowledgements I am grateful to Stephen Robertson and Donna Harman for their comments, and wish speci®cally to acknowledge the latter's scrupulous care in distinguishing her points as from a Referee, ...
doi:10.1016/s0306-4573(99)00044-8
fatcat:lqrad3oravfsxkzahlpj3afmea
JHU/APL at TREC 2001: Experiments in Filtering and in Arabic, Video, and Web Retrieval
2001
Text Retrieval Conference
Preserved Fulltext
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.
Conclusions This year we participated in three tracks that each presented new challenges: filtering, video, and Arabic. ...
We investigated the use of Support Vector Machines (SVMs) for batch text classification and noticed a large sensitivity to parameter settings for these classifiers. ...
This cluster has 200GB of dedicated, networked disk space for use in our retrieval work.
Filtering Track We participated in both the routing and batch tasks for the filtering track. ...
dblp:conf/trec/MayfieldMCPB01
fatcat:mhbbas2scnacxawjtkxdzmijna
TIPSTER phase III accomplishments
1996
Proceedings of a workshop on held at Baltimore, Maryland October 13-15, 1998 -
Preserved Fulltext
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.
art in text processing--are legacies in which all the TIPSTER Government, industry and academic partners can take great pride. ...
Despite the early end of TIPSTER Phase III, the R&D efforts exemplified by the papers in the remainder of these proceedings--and the contributions by participants to the advancements in the state-of-the ...
This test collection supports the main TREC tasks of routing and ad hoc retrieval. ...
doi:10.3115/1119089.1119092
dblp:conf/tipster/Gee98a
fatcat:dwumcoh7kvgnraizgqkdnng4su
Experiments in Japanese text retrieval and routing using the NEAT system
1998
Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '98
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Results on the standard BMIR-Jl and BMIR-J2 Japanese retrieval collections indicate that term weighting transfers well to Japanese text. ...
We also demonstrate that relevance feedback can be used effectively for query expansion in Japanese routing applications. Japanese Character Sets Japanese text contains 3 classes of character: kanji, ...
If more than 5 terms in a row were discarded training for this query was stopped. This training procedure is similar to that used for TREC routing experiments in [22] . ...
doi:10.1145/290941.290992
dblp:conf/sigir/JonesSKS98
fatcat:rgvygdng6bfidlirmagy6sllxe
Evaluation of biomedical text-mining systems: Lessons learned from information retrieval
2005
Briefings in Bioinformatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
One impediment to their development is the lack of systematic and rigorous evaluation, comparable to the approaches developed for information retrieval systems. ...
Biomedical text-mining systems have great promise for improving the efficiency and productivity of biomedical researchers. However, such systems are still not in routine use. ...
Acknowledgments This work was supported by grant ITR-0325160 from the National Science Foundation and earlier grants from the National Library of Medicine. ...
doi:10.1093/bib/6.4.344
pmid:16420733
fatcat:n7p6o2yhnnbezgf5lrgloljsim
FDU at TREC-9: CLIR, Filtering and QA Tasks
2000
Text Retrieval Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This year Fudan University takes part in the TREC-9 conference for the first time. We have participated in three tracks of CLIR, Filtering and QA. We have submitted four runs for CLIR track. ...
For filtering, we participate in the sub-task of adaptive filtering and batch filtering. ...
We are thankful to Yaqian Zhou, Kaijiang Chen, Li Lian and Wei Qian for their help in the implementation of corpus and topic processing, syntactic parser and HMM based English named entity finder. ...
dblp:conf/trec/WuHGLZ00
fatcat:z6s3kgt7pze45p3ukbv6qw4me4
« Previous
Showing results 1 — 15 out of 157 results