Skip to main content

Table 6 Sentence detection.

From: Detection of sentence boundaries and abbreviations in clinical narratives

Method

BL

1

2

3

4

5

6

7

micro-avg. F1 Training

0.78

0.58*'

0.76*'

0.79*'

0.79*

0.82*'

0.90*'

0.92*'

micro-avg. F1 Test

0.75

0.60*'

0.74*'

0.78*'

0.81*'

0.77*'

0.87*'

0.92*'

  1. Evaluation performance per feature set (1 Language features; 2 Rule-based features; 3 Text format features; 4 Word length features; 5 Right context word type features; 6 Word type features; 7 Abbreviation feature). * significant difference to base line (BL) (p <0.05), ' significant difference to predecessor (p <0.05)
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us