From: Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese
Input features | Only words | Capitalization | Prefix + suffix | All three | ||||
---|---|---|---|---|---|---|---|---|
All (%) | OOV (%) | All (%) | OOV (%) | All (%) | OOV (%) | All (%) | OOV (%) | |
Random | 93.59 | 37.98 | 94.65 | 42.73 | 95.89 | 78.41 | 96.93 | 82.61 |
HAL | 93.25 | 44.95 | 94.39 | 49.28 | 95.83 | 78.97 | 96.89 | 83.02 |
NLM | 93.58 | 52.21 | 94.67 | 55.67 | 95.86 | 80.91 | 96.91 | 84.14 |
SG | 93.46 | 50.57 | 94.51 | 53.82 | 95.87 | 80.10 | 96.83 | 83.10 |