Skip to main content

Table 4 Abbreviation detection.

From: Detection of sentence boundaries and abbreviations in clinical narratives

Method

BL

[1]

[1-2]

[1-3]

[1-4]

[1-5]

[1-6]

micro-avg. F1 Training

0.62

0.60*'

0.71*'

0.86*'

0.88*'

0.95*'

0.97*'

micro-avg. F1 Test

0.60

0.60

0.71*'

0.83*'

0.86*

0.93*

0.95*'

  1. Evaluation performance combining feature sets stepwise according to their stand alone performance (1 Rule-based features; 2 Statistical features; 3 Scaling features; 4 Language-dependent features; 5 Length features; 6 Word type features). * significant difference to base line (BL) (p <0.05), ' significant difference to predecessor (p <0.05)