MIT Press

Table 10:

Test accuracy for lemmas that were observed 0, <5, and ≥ 5 times in the TRMor and UD data sets. Tok is the number of tokens with the specified count, Acc is the accuracy using Morse.

	count=0		count<5		count≥5
Dataset	Tok	Acc	Tok	Acc	Tok	Acc
TRMor2006	30	86.67	16	100.0	816	98.9
TRMor2016	79	2.53	579	93.78	18570	98.48
TRMor2018	0	-	1702	82.78	45119	99.48
UD-DA	1019	71.84	1023	94.72	7981	98.93
UD-ES	593	79.26	627	95.37	10780	99.36
UD-FI	2279	61.34	1802	88.85	16989	98.21
UD-RU	1656	77.48	1587	94.39	8305	99.22

	count=0		count<5		count≥5
Dataset	Tok	Acc	Tok	Acc	Tok	Acc
TRMor2006	30	86.67	16	100.0	816	98.9
TRMor2016	79	2.53	579	93.78	18570	98.48
TRMor2018	0	-	1702	82.78	45119	99.48
UD-DA	1019	71.84	1023	94.72	7981	98.93
UD-ES	593	79.26	627	95.37	10780	99.36
UD-FI	2279	61.34	1802	88.85	16989	98.21
UD-RU	1656	77.48	1587	94.39	8305	99.22