Accession Number : AD1004828


Title :   TUW at the First Total Recall Track


Descriptive Note : Conference Paper


Corporate Author : Vienna University of Technology Vienna Austria


Personal Author(s) : Lupu,Mihai


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1004828.pdf


Report Date : 20 Nov 2015


Pagination or Media Count : 9


Abstract : For the first participation in the TREC Total Recall track, we set out to trysome basic changes to the baseline provided by the organisers. Namely, the weightingscheme, the use of stopwords, and the number of learners that contribute to the decisionof which documents to ask the virtual assessor to review. We observed that the baselinewas extremely strong and none of the runs significantly and consistently outperformed it.


Descriptors :   Weighting functions , Information retrieval , Recall , Man machine systems , MACHINE LEARNING , algorithms , Precision


Distribution Statement : APPROVED FOR PUBLIC RELEASE