679 Hits in 2.6 sec

Elicitation and use of relevance feedback information

Olga Vechtomova, Murat Karamuftuoglu
2006 Information Processing & Management  
The paper presents two approaches to interactively refining user search formulations and their evaluation in the new High Accuracy Retrieval from Documents (HARD) track of TREC-12.  ...  The TREC results show that one of the methods is an effective means of interactive query expansion and yields significant performance improvements.  ...  University of Maryland (He & Demner-Fushman, 2004 ) experimented with using either the most informative headline among all documents in each cluster, or merging the headlines of documents in a cluster  ... 
doi:10.1016/j.ipm.2004.10.006 fatcat:vwzaw4chgfgoxosmjh4owczzdu

Large Scale Evaluations of Multimedia Information Retrieval: The TRECVid Experience [chapter]

Alan F. Smeaton
2005 Lecture Notes in Computer Science  
In this presentation and extended abstract we are primarily concerned with MMIR as applied to information in digital video format.  ...  Information Retrieval is a supporting technique which underpins a broad range of content-based applications including retrieval, filtering, summarisation, browsing, classification, clustering, automatic  ...  The author is partly-supported by Science Foundation Ireland under grant 03/IN.3/I361.  ... 
doi:10.1007/11526346_2 fatcat:3on37iw4ergejarzhsxljbblhi

Improving novelty detection for general topics using sentence level information patterns

Xiaoyan Li, W. Bruce Croft
2006 Proceedings of the 15th ACM international conference on Information and knowledge management - CIKM '06  
TREC novelty tracks.  ...  Then we elaborate a thorough analysis of sentence level information patterns on data from the TREC novelty tracks, including sentence lengths, named entities, sentence level opinion patterns.  ...  Experiments were carried out on the data from the TREC novelty tracks 2002-2004.  ... 
doi:10.1145/1183614.1183652 dblp:conf/cikm/LiC06 fatcat:l2iut7pxnrcz3lgbqlv2qr3w5y

Evaluating Retrieval Models through Histogram Analysis

Kriste Krstovski, David A. Smith, Michael J. Kurtz
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
an analysis of ten TREC tasks from the past ten years.  ...  We present a novel approach for efficiently evaluating the performance of retrieval models and introduce two evaluation metrics: Distributional Overlap (DO), which compares the clustering of scores of  ...  Ad-Hoc Retrieval Tasks We conducted experiments using query sets from 4 previous TREC Web Tracks (2009-2012).  ... 
doi:10.1145/2766462.2767821 dblp:conf/sigir/KrstovskiSK15 fatcat:lmehl5ve65b4nom6pn6hxthc2m

TREC genomics special issue overview

William Hersh, Ellen Voorhees
2008 Information retrieval (Boston)  
Acknowledgements The TREC Genomics Track was supported by NSF Grant ITR-0325160. The track also appreciated the help of Lori Buckland and others at NIST for help in its administration.  ...  We were also very grateful to the National Library of Medicine, Highwire Press, and the Mouse Genome Informatics Project for providing data for use in the track.  ...  The track also drew upon experience in passage retrieval from the previous TREC High Accuracy Retrieval from Documents (HARD) Track (Allan 2003 (Allan , 2004 .  ... 
doi:10.1007/s10791-008-9076-6 fatcat:e36xnnbro5eqvkmmm7x4rxj2mu

What makes a query difficult?

David Carmel, Elad Yom-Tov, Adam Darlow, Dan Pelleg
2006 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06  
In the absence of knowledge about one of the model components, the model is still useful by approximating the missing component based on the other components.  ...  One of the tasks in the 2004 and 2005 TREC Robust tracks was to estimate the relative difficulty of each topic.  ...  In the Robust tracks of 2003 and 2004, systems were challenged by 50 old TREC topics found to be "difficult" for most systems over the years.  ... 
doi:10.1145/1148170.1148238 dblp:conf/sigir/CarmelYDP06 fatcat:k5y2rmgxbzarfb2pqdj2dxjaoq

An information-pattern-based approach to novelty detection

Xiaoyan Li, W. Bruce Croft
2008 Information Processing & Management  
Experiments on novelty detection on 15 data from the TREC 2002, 2003 and 2004 novelty tracks show that the proposed approach significantly improves the 16 performance of novelty detection in terms of precision  ...  Second, a thorough analysis of sen-12 tence level information patterns is elaborated using data from the TREC novelty tracks, including sentence lengths, named 13 entities (NEs), and sentence level opinion  ...  Question formulation 558 There are 49 queries in the TREC 2002 novelty track, 50 queries in the TREC 2003 novelty track and 50 559 queries in the TREC 2004 novelty track.  ... 
doi:10.1016/j.ipm.2007.09.013 fatcat:ko2fvnhmbnek5hbm5xpmdgmmrm

Text similarity: an alternative way to search MEDLINE

J. Lewis, S. Ossowski, J. Hicks, M. Errami, H. R. Garner
2006 Bioinformatics  
A variety of other derivative systems and visualization tools provides the user with an enhanced experience and additional capabilities.  ...  Several text similarity search algorithms, both standard and novel, were implemented and tested in order to determine which obtained the best results in information retrieval exercises.  ...  Results from 150 queries from TREC routing 2, 3 and Hard Track 2003, calculated with TREC evaluation tool.  ... 
doi:10.1093/bioinformatics/btl388 pmid:16926219 fatcat:gl6usfhjqnbw7f7jof352av65q

Less is more

Harr Chen, David R. Karger
2006 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06  
While doing so may be computationally intractable, we show that a simple greedy optimization algorithm that approximately optimizes the given objectives produces rankings for TREC queries that outperform  ...  However, there are many scenarios in which that ranking does not optimize for the user's information need.  ...  Robust Track Experiments We turn our attention to the TREC 2004 robust track.  ... 
doi:10.1145/1148170.1148245 dblp:conf/sigir/ChenK06 fatcat:rm72qke75zfqlntkfogkqdrry4

Query Expansion for Language Modeling Using Sentence Similarities [chapter]

Debasis Ganguly, Johannes Leveling, Gareth J. F. Jones
2011 Lecture Notes in Computer Science  
Additional experiments on the challenging search topics of the TREC-2004 Robust track show that the new method is able to improve MAP by 5.7% without the use of external resources and query hardness prediction  ...  IR experiments on the TREC ad-hoc retrieval test collections using the sentence based query expansion (SBQE) show a significant increase in Mean Average Precision (MAP) compared to baselines obtained using  ...  The following subsection aims to investigate the effectiveness of SBQE on the hard topics of the TREC 2004 Robust Track.  ... 
doi:10.1007/978-3-642-21353-3_6 fatcat:bzyiwhshereb5ck3vmha6kppie

Solr Integration in the Anserini Information Retrieval Toolkit

Ryan Clancy, Toke Eskildsen, Nick Ruest, Jimmy Lin
2019 Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR'19  
In this demonstration, we examine different architectures for Solr integration in order to address two current limitations of the system: the lack of an interactive search interface and support for distributed  ...  Two architectures are explored: In the first approach, Anserini is used as a frontend to index directly into a running Solr instance.  ...  This work was supported in part by the Natural Sciences and Engineering Research Council (NSERC) of Canada, the Canada Foundation for Innovation Leaders Fund, and the Ontario Research Fund.  ... 
doi:10.1145/3331184.3331401 dblp:conf/sigir/ClancyERL19 fatcat:j6afggtnf5fajlvehbd5olc7n4

Novelty detection based on sentence level patterns

Xiaoyan Li, W. Bruce Croft
2005 Proceedings of the 14th ACM international conference on Information and knowledge management - CIKM '05  
An analysis of patterns in sentences was performed with data from the TREC 2002 novelty track and experiments on novelty detection were carried out on data from the TREC 2003 and 2004 novelty tracks.  ...  The detection of new information in a document stream is an important component of many potential applications.  ...  the TREC 2003 novelty track and 50 queries in the TREC 2004 novelty track.  ... 
doi:10.1145/1099554.1099734 dblp:conf/cikm/LiC05a fatcat:bwa7oozkzvfunj6qr3kix5jqiu

When will information retrieval be "good enough"?

James Allan, Ben Carterette, Joshua Lewis
2005 Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '05  
, but more experiments are needed to examine the area around that threshold closely.  ...  Subjects performed the task by using these ranked lists to guide their labeling of answer passages in the retrieved articles.  ...  We adopted the binary preference ("bpref") measure that is used for passage retrieval evaluation in the TREC 2004 HARD track [2] , because it has been shown both to track mean average precision in ranking  ... 
doi:10.1145/1076034.1076109 dblp:conf/sigir/AllanCL05 fatcat:gdglx4yupnadtj5cr5qffuydhm

Where do good query terms come from?

Gheorghe Muresan, Dmitri Roussinov
2007 Proceedings of the American Society for Information Science and Technology  
This explains why, in the HARD track of TREC 2005, the overall conclusion was that interaction with the searcher and elicitation of additional information could not over-perform automatic procedures for  ...  This paper describes a framework for investigating the quality of different query expansion approaches, and applies it in the HARD TREC experimental setting.  ...  Interactive Elicitations In our HARD TREC 2005 work we were inspired by Rutgers work in the Interactive tracks of TREC (Belkin, et al., 2002 (Belkin, et al., , 2003 and UNC work in HARD TREC 2004 (Kelly  ... 
doi:10.1002/meet.14504301197 fatcat:wwxrzsrmdbhnde2bx6g5r27x4a

Redundant documents and search effectiveness

Yaniv Bernstein, Justin Zobel
2005 Proceedings of the 14th ACM international conference on Information and knowledge management - CIKM '05  
We show, moreover, that content-equivalent documents have a significant effect on the search experience: we found that 16.6% of all relevant documents in runs submitted to the TREC 2004 terabyte track  ...  The presence of such mutually redundant documents in search results can degrade the user search experience.  ...  An example of a document that occurred 300 times is in Figure 3. EQUIVALENCE IN SEARCH RESULTS The TREC terabyte track (Clarke et al. 2004 ) ran for the first time in 2004.  ... 
doi:10.1145/1099554.1099733 dblp:conf/cikm/BernsteinZ05 fatcat:3vv7oji4y5ejtfcafd2f3mjfcq
« Previous Showing results 1 — 15 out of 679 results