A comparative analysis of retrieval features used in the TREC 2006 Genomics Track passage retrieval task Export

@article{18693910, abstract = {OBJECTIVE: Identify the set of features that best explained the variation in the performance measure of TREC 2006 Genomics information extraction task, Mean Average Passage Precision (MAPP). METHODS: A multivariate regression model was built using a backward-elimination approach as a function of certain generalized features that were common to all the algorithms used by TREC 2006 Genomics track participants. RESULTS: Our regression analysis found that the following four factors were collectively associated with variation in MAPP: (1) Normalization of keywords in the query (2) Use of Entrez gene thesaurus for synonymous terms look-up (3) Unit of text retrieved using respective IR algorithms and (4) The way a passage was defined. CONCLUSION: These reasonably likely hypotheses, generated by an exploratory data analysis, are informative in understanding results of the TREC 2006 Genomics passage extraction task. This approach has general value for analyzing the results of similar common challenge tasks.}, address = {Department of Medical Informatics \& Clinical Epidemiology, Oregon Health \& Science University, Portland, OR 97239, USA.}, author = {Rekapalli, H. K. and Cohen, A. M. and Hersh, W. R.}, citeulike-article-id = {4415961}, day = {1}, issn = {1559-4076}, journal = {AMIA Annual Symposium proceedings / AMIA Symposium AMIA Symposium}, keywords = {abstracting, algorithms, analysis, and, as, controlled, databases, file-import-09-04-28, genomics, headings, indexing, information, multivariate, regression, retrieval, storage, subject, topic, vocabulary}, month = {January}, pages = {620--4}, pdf = {file://localhost/Users/hpiwowar/Documents/Papers/2007/Rekapalli/AMIA\%20Annual\%20Symposium\%20proceedings\%20AMIA\%20Symposium\%20AMIA\%20Symposium\%202007\%20Rekapalli.pdf}, posted-at = {2009-04-28 16:01:18}, priority = {2}, title = {A comparative analysis of retrieval features used in the TREC 2006 Genomics Track passage retrieval task}, year = {2007} }

TY - JOUR ID - 18693910 L3 - citeulike-article-id:4415961 N2 - OBJECTIVE: Identify the set of features that best explained the variation in the performance measure of TREC 2006 Genomics information extraction task, Mean Average Passage Precision (MAPP). METHODS: A multivariate regression model was built using a backward-elimination approach as a function of certain generalized features that were common to all the algorithms used by TREC 2006 Genomics track participants. RESULTS: Our regression analysis found that the following four factors were collectively associated with variation in MAPP: (1) Normalization of keywords in the query (2) Use of Entrez gene thesaurus for synonymous terms look-up (3) Unit of text retrieved using respective IR algorithms and (4) The way a passage was defined. CONCLUSION: These reasonably likely hypotheses, generated by an exploratory data analysis, are informative in understanding results of the TREC 2006 Genomics passage extraction task. This approach has general value for analyzing the results of similar common challenge tasks. JF - AMIA Annual Symposium proceedings / AMIA Symposium AMIA Symposium SN - 1559-4076 AD - Department of Medical Informatics & Clinical Epidemiology, Oregon Health & Science University, Portland, OR 97239, USA. EP - 4 TI - A comparative analysis of retrieval features used in the TREC 2006 Genomics Track passage retrieval task SP - 620 KW - abstracting KW - algorithms KW - analysis KW - and KW - as KW - controlled KW - databases KW - file-import-09-04-28 KW - genomics KW - headings KW - indexing KW - information KW - multivariate KW - regression KW - retrieval KW - storage KW - subject KW - topic KW - vocabulary AU - Rekapalli, HK AU - Cohen, AM AU - Hersh, WR PY - 2007/01/01/ ER -