Skip to main content

Table 4 Structured abstracts discourse label prediction based on an AdaBoostM1 model

From: GeneRIF indexing: sentence selection based on machine learning

Discourse

Positives

TP

FP

Precision

Recall

F-measure

Background

18875

11045

8820

0.5560

0.5852

0.5702

Conclusions

53396

37402

12844

0.7444

0.7005

0.7218

Methods

85764

69003

21382

0.7634

0.8046

0.7835

Objective

26425

19237

7883

0.7093

0.7280

0.7185

Results

117546

93250

29424

0.7601

0.7933

0.7764

  1. Results of an AdaBoostM1 classifier trained on structured abstracts. For each label we show the number of instances in the data set for each label (Positives), the number of True Positives (TP), the number of False Positives (FP) and the precision, recall and F-measure values.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us