BMC Medical Informatics and Decision Making

Table 2 Automatic word alignment results from batch 1

From: Creating a medical dictionary using word alignment: The influence of sources and resources

Batch	Run	Resources																	Alignment							Result
		Static			Statistic							Dynamic
		Stan	POS	MeSH	Statistic partition							Training partition							Test partition							Recall	Precision	F-score
					2	3	4	5	6	7	8	2	3	4	5	6	7	8	2	3	4	5	6	7	8
1	1				X														X							0.54	0.56	0.55
1	2					X														X						0.48	0.56	0.52
1	3						X														X					0.38	0.41	0.39
1	4							X														X				0.43	0.48	0.45
1	5								X														X			0.41	0.46	0.43
1	6									X														X		0.40	0.36	0.38
1	7										X														X	0.46	0.52	0.49
1	8	X	X	X	X														X							0.68	0.68	0.68
1	9	X	X	X		X														X						0.72	0.75	0.73
1	10	X	X	X			X														X					0.60	0.60	0.60
1	11	X	X	X				X														X				0.69	0.67	0.68
1	12	X	X	X					X														X			0.65	0.64	0.64
1	13	X	X	X						X														X		0.53	0.48	0.50
1	14	X	X	X							X														X	0.71	0.71	0.71
1	15	X	X	X	X							X							X							0.72	0.70	0.71
1	16	X	X	X		X							X							X						0.80	0.80	0.80
1	17	X	X	X			X							X							X					0.71	0.68	0.69
1	18	X	X	X				X							X							X				0.80	0.78	0.79
1	19	X	X	X					X							X							X			0.83	0.78	0.80
1	20	X	X	X						X							X							X		0.63	0.58	0.60
1	21	X	X	X							X							X							X	0.84	0.85	0.84

Recall, precision and F-score from the automatic word alignment when resources for the automatic word alignment were generated from the same partition as the aligned partition. The configurations CfStatistical, CfStatisticalStatic and CfStatisticalStaticTraining were used.

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com