Table 5

Evaluation results. Case 1 is using the dictionary feature. Case 2 is not using the dictionary feature. "TP", "FP", and "FN" are the numbers of true-positives, false-positives, and false-negatives.


run
Precision
Recall
Balanced f-score
TP
FP
FN


1st
0.8245
0.7416
0.7809
4412
939
1537
case 1
2nd
0.8230
0.7433
0.7811
4422
951
1527

3rd
0.8225
0.7408
0.7795
4407
951
1542

case 2
without dictionary matching
0.8122
0.7075
0.7562
4209
973
1740

Mitsumori et al. BMC Bioinformatics 2005 6(Suppl 1):S8   doi:10.1186/1471-2105-6-S1-S8