Skip to main content

Table 5 Performance of CombSUM

From: A robust approach to optimizing multi-source information for enhancing genomics retrieval performance

Component

document

aspect

passage2

Best of baselines

0.2906

0.2189

0.0988

UniNE1+York07ga2+kyoto1

0.2692 (-7.36%)

0.1552 (-29.07%)

0.0939 (-4.94%)

UniNE1+York07ga2+UBexp1

0.2690 (-7.41%)

0.1840 (-15.94%)

0.0944 (-4.49%)

UniNE1+MuMshFd+kyoto1

0.2567 (-11.66%)

0.1809 (-17.35%)

0.0985 (-0.30%)

UniNE1+MuMshFd+UBexp1

0.2630 (-9.49%)

0.1919 (-12.32%)

0.0991 (0.30%)

  1. We evaluate the combinations applying the CombSUM method in this table. The values in the parentheses are the relative rates of improvement over the best results of the baselines.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us