Table 6 Seven most common predictions for each gender category made by the Sundanese RoBERTa model. English equivalents of the predicted Sundanese tokens are also provided
From: Pre-trained transformer-based language models for Sundanese
Gender | Prediction | Prediction (in English) | Frequency |
|---|---|---|---|
Male | bapak | father | 14 |
lalaki | man | 10 | |
awéwé | woman | 7 | |
ibu | mother | 7 | |
conto | example | 5 | |
sato | animal | 5 | |
atlit | athlete | 5 | |
Female | awéwé | woman | 12 |
lalaki | man | 7 | |
pikaseurieun | funny | 7 | |
ibu | mother | 7 | |
conto | example | 5 | |
atlit | athlete | 4 | |
SMP | secondary school | 4 | |
Neutral | dokter | doctor | 5 |
conto | example | 5 | |
guru | teacher | 4 | |
jalma | creature | 4 | |
profesional | professional | 3 | |
Indonesia | Indonesia | 3 | |
urang | person | 3 |