CoolFace
Modelpublic

benjamin/roberta-base-wechsel-ukrainian

sourceHugging Facemitupdated 4y agoView on Hugging Face
0likes57downloads
Model Card

roberta-base-wechsel-ukrainian

`roberta-base` transferred to Ukrainian using the method from the NAACL2022 paper WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Evaluation

Evaluation was done on lang-uk's ner-uk project, the Ukrainian portion of WikiANN and the Ukrainian IU corpus from the Universal Dependencies project. Evaluation results are the mean of 5 runs with different seeds.

_Validation Results_

lang-uk NER (Micro F1)WikiANN (Micro F1)UD Ukrainian IU POS (Accuracy)
roberta-base-wechsel-ukrainian88.06 (0.50)92.96 (0.08)98.70 (0.05)
roberta-large-wechsel-ukrainian_89.27 (0.53)__93.22 (0.15)__98.86 (0.03)_
roberta-base-scratch-ukrainian*85.49 (0.88)91.91 (0.08)98.49 (0.04)
roberta-large-scratch-ukrainian*86.54 (0.70)92.39 (0.16)98.65 (0.09)
dbmdz/electra-base-ukrainian-cased-discriminator87.49 (0.52)93.20 (0.16)98.60 (0.03)
xlm-roberta-base86.68 (0.44)92.41 (0.13)98.53 (0.02)
xlm-roberta-large86.64 (1.61)93.01 (0.13)98.71 (0.04)

_Test Results_

lang-uk NER (Micro F1)WikiANN (Micro F1)UD Ukrainian IU POS (Accuracy)
roberta-base-wechsel-ukrainian90.81 (1.51)92.98 (0.12)98.57 (0.03)
roberta-large-wechsel-ukrainian_91.24 (1.16)__93.22 (0.17)__98.74 (0.06)_
roberta-base-scratch-ukrainian*89.57 (1.01)92.05 (0.09)98.31 (0.08)
roberta-large-scratch-ukrainian*89.96 (0.89)92.49 (0.15)98.52 (0.04)
dbmdz/electra-base-ukrainian-cased-discriminator90.43 (1.29)92.99 (0.11)98.59 (0.06)
xlm-roberta-base90.86 (0.81)92.27 (0.09)98.45 (0.07)
xlm-roberta-large90.16 (2.98)92.92 (0.19)98.71 (0.04)

\trained using the same exact training setup as the wechsel-\ models, but without parameter transfer from WECHSEL.

License

MIT