A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools

Table 16 Sentence boundary detection results on the CRAFT public release data (70% set)

Sentence boundary detector	Precision	Recall	F-measure
LingPipe	0.98	0.98	0.98
OpenNLP	0.87	0.74	0.80
UIMA-native	0.85	0.75	0.80

ISSN: 1471-2105