Skip to main content

Table 6 Comparison with the state-of-the-art PRF retrieval models in certain metrics

From: An adaptive term proximity based rocchio’s model for clinical decision support retrieval

 PRoc2PRoc3TF-PRFHRoc1
MAP0.06000.05930.05800.0651 +# (8.50%,9.78%,12.24%)
P@50.28670.26670.26000.2933 +# (2.30%,9.97%,12.81%)
P@100.25330.23000.24670.2733 +# (7.90%,18.83%,10.78%)
P@200.24170.21670.23170.2350 +# (-2.77%,8.44%,1.42%)
F10.10310.10200.10120.1112 +# (7.86%,9.02%,9.88%)
  1. The best result obtained is shown in bold, and the superscripts “*”, “+” and “#” denote statistically significant improvements over PRoc2, PRoc3 and TF-PRF, respectively (Wilcoxon signed-rank test with p<0.05). The values in parentheses are the improvements over RM3, BM25+Rocchio, PRoc2 and TF-PRF, respectively