MIT Press

Skip to Main Content

Table 3:

German number classification accuracy, with standard errors computed from 200 random train-test splits. ‘subs.’ marks in-vocabulary subset evaluation, not comparable to the other results.

	train classes	test classes
	-n/-s/-e	-r	Umlaut
Random	50.0	50.0	50.0
Autoencoder	61.4 (± 0.9)	50.7 (± 0.8)	51.9 (± 0.4)
LSTM	71.5 (± 0.8)	78.8 (± 0.6)	60.8 (± 0.6)
RNN	65.4 (± 0.9)	59.8 (± 1.0)	56.7 (± 0.7)
WordNLM	77.3 (± 0.7)	77.1 (± 0.5)	74.2 (± 0.6)
WordNLM_subs.	97.1 (± 0.3)	90.7 (± 0.1)	97.5 (± 0.1)

	train classes	test classes
	-n/-s/-e	-r	Umlaut
Random	50.0	50.0	50.0
Autoencoder	61.4 (± 0.9)	50.7 (± 0.8)	51.9 (± 0.4)
LSTM	71.5 (± 0.8)	78.8 (± 0.6)	60.8 (± 0.6)
RNN	65.4 (± 0.9)	59.8 (± 1.0)	56.7 (± 0.7)
WordNLM	77.3 (± 0.7)	77.1 (± 0.5)	74.2 (± 0.6)
WordNLM_subs.	97.1 (± 0.3)	90.7 (± 0.1)	97.5 (± 0.1)