MIT Press

Table 3:

Results for comparing base model with previous work. Bayesian and NeuroCipher are the models proposed by Snyder et al. (2010) and Luo et al. (2019), respectively. Ugaritic results for previous work are taken from their papers. For NeuroCipher, we run the authors’ public implementation to obtain the results for Gothic.

Lost	Ugaritic^{^†}	Gothic
Known	Hebrew	PG	ON	OE
Bayesian	0.604	–	–	–
NeuroCipher	0.659	0.753	0.543	0.313
base	0.778	0.865	0.558	0.472

Lost	Ugaritic^{^†}	Gothic
Known	Hebrew	PG	ON	OE
Bayesian	0.604	–	–	–
NeuroCipher	0.659	0.753	0.543	0.313
base	0.778	0.865	0.558	0.472

^†

A@1 is reported for Ugaritic to make direct comparison with previous work. A@10 is still used for Gothic experiments.

View Large

This Feature Is Available To Subscribers Only