. 2021 May 5;9(5):e24678. doi: 10.2196/24678

Table 5.

Post-hoc analysis of variance (ANOVA) of the named entity recognition models: P values of two-tailed paired t tests for each pair of models.^a

Named entity recognition	PWE^b, P value	PWE+CE^c, P value	PWE+SFE^d, P value
RIWE^e	<.001	<.001	<.001
PWE	N/A^f	.94	.99
PWE+CE	N/A	N/A	.95

^aRIWE is significantly worse than the rest of the models. At the same time, there is no statistically significant difference between PWE, PWE+CE, and PWE+SFE.

^bPWE: pretrained word embeddings.

^cCE: character embedding.

^dSFE: semantic-feature embeddings.

^eRIWE: randomly initialized word embeddings.

^fN/A: not applicable.