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

Table 5 Automatic word alignment results from batch 4

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
4	1	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X							0.73	0.71	0.72
4	2	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X		X						0.81	0.81	0.81
4	3	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X			X					0.81	0.76	0.78
4	4	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X				X				0.81	0.78	0.79
4	5	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X					X			0.84	0.79	0.81
4	6	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X						X		0.74	0.65	0.69
4	7	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X	X							X	0.85	0.85	0.85

Recall, precision and F-score from the automatic word alignment when resources for the automatic word alignment were generated from all partitions and a single partition was automatically aligned. The configuration CfStatisticalStaticTraining was used.

ISSN: 1472-6947