Treebank Statistics: UD_Middle_Armenian-ArmTDP: Features: NumForm
This feature is language-specific.
It occurs with 3 different values: Armenian, Digit, Word.
98 tokens (2%) have a non-empty value of NumForm.
48 types (3%) occur at least once with a non-empty value of NumForm.
48 lemmas (4%) occur at least once with a non-empty value of NumForm.
The feature is used with 2 part-of-speech tags: NUM (96; 2% instances), ADJ (2; 0% instances).
NUM
96 NUM tokens (100% of all NUM tokens) have a non-empty value of NumForm.
The most frequent other feature values with which NUM and NumForm co-occurred: NumType=Card (95; 99%).
NUM tokens may have the following values of NumForm:
Armenian(20; 21% of non-emptyNumForm): Բ, Գ, ԳՃ, Դ, ԷՃԽԵ, Թ, Ծ, ԾԱ, Կ, ԿԴDigit(10; 10% of non-emptyNumForm): 2, 1279, 1296, 3, 4, 9Word(66; 69% of non-emptyNumForm): երեք, երկու, մէկ, տասն, չորս, ինն, քսան, Տասնեւյոթ, Տասնեւութ, Տասնհինգ
NumForm seems to be lexical feature of NUM. 100% lemmas (46) occur only with one value of NumForm.
ADJ
2 ADJ tokens (1% of all ADJ tokens) have a non-empty value of NumForm.
The most frequent other feature values with which ADJ and NumForm co-occurred: Degree=EMPTY (2; 100%).
ADJ tokens may have the following values of NumForm:
Word(2; 100% of non-emptyNumForm): Առաջին, Երկրորդ
Relations with Agreement in NumForm
The 10 most frequent relations where parent and child node agree in NumForm:
NUM –[flat]–> NUM (2; 100%),
NUM –[flat:range]–> NUM (1; 100%).