82 Hits in 4.3 sec

Report on the TREC 2005 Experiment: Genomics Track

Patrick Ruch, Frédéric Ehrler, Samir Abdou, Jacques Savoy
2005 Text Retrieval Conference  
This year, for our participation to the TREC Genomics track, we participated in the two tasks: the ad hoc and the categorization task.  ...  This papers focuses on the ad hoc task, while experiments conducted for task 2 are described in the Aronson and al. 2005. Task I.  ...  John Wilbur for the fruitful discussions we had during our joint TREC meeting at the NLM.  ... 
dblp:conf/trec/RuchEAS05 fatcat:hwo4tsgpb5bmvoyoqnotkfoefy

Synonym-Based Expansion and Boosting-Based Re-Ranking: A Two-phase Approach for Genomic Information Retrieval

Zhongmin Shi, Baohua Gu, Fred Popowich, Anoop Sarkar
2005 Text Retrieval Conference  
We describe in this paper the design and evaluation of the system built at Simon Fraser University for the TREC 2005 adhoc retrieval task in the Genomics track.  ...  we integrated En-trezGene, HUGO, Eugenes, ARGH, GO, MeSH, UMLSKS and WordNet into a large reference database and then used a conventional Information Retrieval (IR) toolkit, the Lemur toolkit (Lemur, 2005  ...  We greatly acknowledge the organization committee of the TREC 2005 genomics track and those who participated in the topic generation and relevance judgment for their valuable work.  ... 
dblp:conf/trec/ShiGPS05 fatcat:ieapm6lh7ncgrg6fxxlp7lqq3u

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 ad hoc retrieval task ran in the TREC 2004 (Hersh et al. 2004 , 2006a ) and TREC 2005 (Hersh et al. 2005 ) Genomics Tracks.  ... 
doi:10.1007/s10791-008-9076-6 fatcat:e36xnnbro5eqvkmmm7x4rxj2mu

UM-D at TREC 2005: Genomics Track

Liping Huang, ZhiHang Chen, Yi Lu Murphey
2005 Text Retrieval Conference  
Ad hoc Retrieval Task Overview The genomics track of TREC 2005 consisted of two tasks: ad hoc retrieval task and categorization task.  ...  Introduction The University of Michigan-Dearborn team participated in the ad hoc task and submitted two runs in TREC 2005.  ...  Experiment The performance of our two runs for 50 topics is shown in the  ... 
dblp:conf/trec/HuangCM05 fatcat:b6nrmvjgrza2rb2izbqh6jtqmm

Exploring criteria for successful query expansion in the genomic domain

Nicola Stokes, Yi Li, Lawrence Cavedon, Justin Zobel
2008 Information retrieval (Boston)  
Overall TREC Genomics Track results are also mixed; however, results from the top performing systems provide strong evidence supporting the need for expansion.  ...  Using this framework, we compare and contrast the effectiveness of a variety of biomedical knowledge sources used by TREC 2006 Genomics Track participants for expansion.  ...  Query Expansion Frameworks at the TREC Genomics Track In Section ??, we briefly discussed related work on query expansion for medical IR.  ... 
doi:10.1007/s10791-008-9073-9 fatcat:rpfredqpjzdulds7b7q5qrjuhq

Experiment Report of TREC 2005 Genomics Track ad hoc Retrieval Task

Wei Zhou, Clement T. Yu
2005 Text Retrieval Conference  
This report describes the experiments we have conducted on the ad hoc retrieval task of Genomics track at TREC 2005.  ...  In the experiment, a number of different techniques were employed, including Porter stemming, MeSH term and gene name identification, Okapi, weighting schemes, query expansion, and concept-based ranking  ...  Introduction The purpose of the ad hoc retrieval task of Genomics track at TREC 2005 is to provide systems with better-defined queries (each query is derived from a generic topic template which includes  ... 
dblp:conf/trec/ZhouY05 fatcat:ao5ptrbsrjajdbfqtl3smkhrcm

An empirical study of tokenization strategies for biomedical information retrieval

Jing Jiang, ChengXiang Zhai
2007 Information retrieval (Boston)  
In particular, it is shown that different query types require different tokenization heuristics, stemming is effective only for certain queries, and stop word removal in general does not improve the retrieval  ...  In this work, we conducted a careful, systematic evaluation of a set of tokenization heuristics on all the available TREC biomedical IR test collections with two representative retrieval methods.  ...  RELATED WORK Most previous work on biomedical IR appeared in the Genomics Track in TREC 2003 TREC , 2004 TREC and 2005 .  ... 
doi:10.1007/s10791-007-9027-7 fatcat:xt7uopccvnhpxnwm5ju762w7za

Knowledge-intensive conceptual retrieval and passage extraction of biomedical literature

Wei Zhou, Clement Yu, Neil Smalheiser, Vetle Torvik, Jie Hong
2007 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07  
in the Genomics Track of TREC 2006.  ...  Based on the TREC platform, we show that appropriate use of domainspecific knowledge in a proposed conceptual retrieval model yields about 23% improvement over the best reported result in passage retrieval  ...  Data sets and evaluation metrics Our experiments were performed on the platform of the Genomics track of TREC 2006.  ... 
doi:10.1145/1277741.1277853 dblp:conf/sigir/ZhouYSTH07 fatcat:k263t2werjbb3icrwf4arvq6hm

Enhancing access to the Bibliome: the TREC 2004 Genomics Track

William R Hersh, Ravi Teja Bhupatiraju, Laura Ross, Phoebe Roberts, Aaron M Cohen, Dale F Kraemer
2006 Journal of Biomedical Discovery and Collaboration  
The TREC Genomics Track and its test collection resources provide tools that allow improvement in information retrieval systems.  ...  The goal of the TREC Genomics Track is to improve information retrieval in the area of genomics by creating test collections that will allow researchers to improve and better understand failures of their  ...  Acknowledgements The TREC 2004 Genomics Track was supported by NSF Grant ITR-0325160.  ... 
doi:10.1186/1747-5333-1-3 pmid:16722581 pmcid:PMC1440302 fatcat:47rfw3fwafa3nm2huaaxu57de4

Factors affecting the effectiveness of biomedical document indexing and retrieval based on terminologies

Duy Dinh, Lynda Tamine, Fatiha Boubekeur
2013 Artificial Intelligence in Medicine  
For example, tested on the 2005 TREC Genomics collection, our multi-terminology based IR approach provides an improvement rate of +6.98% in terms of MAP (mean average precision) (p < 0.05) compared to  ...  Objective: The aim of this work is to evaluate a set of indexing and retrieval strategies based on the integration of several biomedical terminologies on the available TREC Genomics collections for an  ...  Acknowledgements We would like to thank people at the IRIT laboratory who develop and maintain the OSIRIM platform, which is an infrastructure of several interconnected computers for undertaking experimental  ... 
doi:10.1016/j.artmed.2012.08.006 pmid:23092678 fatcat:2ss3cba3njfhzpk76rbd6isuga

UIUC/MUSC at TREC 2005 Genomics Track

ChengXiang Zhai, Xu Ling, Xin He, Atulya Velivelli, Xuanhui Wang, Hui Fang, Azadeh Shakery, Xinghua Lu
2005 Text Retrieval Conference  
We report experiment results from the collaborative participation of UIUC and MUSC in the TREC 2005 Genomics Track.  ...  Experiment results show that a structured theme-based language modeling approach is effective in improving retrieval effectiveness for the ad hoc taks and the Latent Dirichlet Allocation method is effective  ...  Introduction The University of Illinois at Urbana-Champaign (UIUC) and Medical University of South Carolina (MUSC) collaborated on both tasks of TREC 2005 Genomics Track with UIUC being more focused on  ... 
dblp:conf/trec/ZhaiLHVWFSL05 fatcat:u47ycibumffxbbnsdtutook7da

An empirical study of gene synonym query expansion in biomedical information retrieval

Yue Lu, Hui Fang, Chengxiang Zhai
2008 Information retrieval (Boston)  
Our experiment results show that synonym expansion can significantly improve the retrieval accuracy.  ...  TREC biomedical text collections for ad hoc document retrieval.  ...  Acknowledgments This material is based in part upon work supported by the National Science Foundation under award number 0425852 and work supported by NIH/NLM grant 1 R01 LM009153-01.  ... 
doi:10.1007/s10791-008-9075-7 fatcat:luqi4sdwenepzlfkt4rxf65f7y

TREC 2006 Genomics Track Overview

William R. Hersh, Aaron M. Cohen, Phoebe M. Roberts, Hari Krishna Rekapalli
2006 Text Retrieval Conference  
The TREC Genomics Track implemented a new task in 2006 that focused on passage retrieval for question answering using full-text documents from the biomedical literature.  ...  The performance of submitted runs was scored using mean average precision (MAP) at the passage, aspect, and document level.  ...  Acknowledgements The TREC Genomics Track is funded by grant ITR-0325160 from the U.S. National Science Foundation.  ... 
dblp:conf/trec/HershCRR06 fatcat:jfugykj3vvhv3h4jtc7scuk4fi

Finding Relevant Passages in Scientific Articles: Fusion of Automatic Approaches vs. an Interactive Team Effort

Dina Demner-Fushman, Susanne M. Humphrey, Nicholas C. Ide, Russell F. Loane, Patrick Ruch, Miguel E. Ruiz, Lawrence H. Smith, Lorraine K. Tanabe, W. John Wilbur, Alan R. Aronson
2006 Text Retrieval Conference  
To continue using our TREC 2005 fusion approach, we needed a common representation for the full text biomedical articles to be shared by the four base systems (Essie, SMART, EasyIR and Theme.)  ...  The fusion run outperformed Essie, the best of the base systems, at 94% to 99% significance level, with the exception of passage precision.  ...  The topics for the 2006 genomics track are questions based on the Generic Topic Types (GTTs).  ... 
dblp:conf/trec/Demner-FushmanHILSTWADRR06 fatcat:m7gfptuajvfzpgxvl7b2flulbi

MeSH Based Feedback, Concept Recognition and Stacked Classification for Curation Tasks

Wessel Kraaij, Stephan Raaijmakers, Marc Weeber, Rob Jelier
2004 Text Retrieval Conference  
This paper reports about experiments carried out in the context of the genomics track at TREC 2004. Experiments were concentrated on two subtasks: the ad hoc retrieval task and the triage task.  ...  Experiments for the ad hoc task aimed at improving a standard full-text ad-hoc run (using a language modeling approach) by exploiting the manual classification of MEDLINE abstracts (the MeSH terms) for  ...  abbreviation expansion algorithm to resolve abbreviations, and thus potentially reducing gene symbol ambiguity.  ... 
dblp:conf/trec/KraaijRWJ04 fatcat:ac2axngh4zcl5cakvn5l4d7kfa
« Previous Showing results 1 — 15 out of 82 results