|
|
|
--- |
|
language: |
|
- la |
|
license: apache-2.0 |
|
library_name: transformers |
|
tags: |
|
- part-of-speech |
|
- token-classification |
|
datasets: |
|
- universal_dependencies |
|
metrics: |
|
- accuracy |
|
|
|
model-index: |
|
- name: xlm-roberta-base-ft-udpos28-la |
|
results: |
|
- task: |
|
type: token-classification |
|
name: Part-of-Speech Tagging |
|
dataset: |
|
type: universal_dependencies |
|
name: Universal Dependencies v2.8 |
|
metrics: |
|
- type: accuracy |
|
name: English Test accuracy |
|
value: 81.5 |
|
- type: accuracy |
|
name: Dutch Test accuracy |
|
value: 79.6 |
|
- type: accuracy |
|
name: German Test accuracy |
|
value: 78.2 |
|
- type: accuracy |
|
name: Italian Test accuracy |
|
value: 78.0 |
|
- type: accuracy |
|
name: French Test accuracy |
|
value: 78.1 |
|
- type: accuracy |
|
name: Spanish Test accuracy |
|
value: 79.8 |
|
- type: accuracy |
|
name: Russian Test accuracy |
|
value: 89.8 |
|
- type: accuracy |
|
name: Swedish Test accuracy |
|
value: 86.0 |
|
- type: accuracy |
|
name: Norwegian Test accuracy |
|
value: 81.5 |
|
- type: accuracy |
|
name: Danish Test accuracy |
|
value: 85.7 |
|
- type: accuracy |
|
name: Low Saxon Test accuracy |
|
value: 56.6 |
|
- type: accuracy |
|
name: Akkadian Test accuracy |
|
value: 44.7 |
|
- type: accuracy |
|
name: Armenian Test accuracy |
|
value: 86.4 |
|
- type: accuracy |
|
name: Welsh Test accuracy |
|
value: 65.1 |
|
- type: accuracy |
|
name: Old East Slavic Test accuracy |
|
value: 79.8 |
|
- type: accuracy |
|
name: Albanian Test accuracy |
|
value: 74.9 |
|
- type: accuracy |
|
name: Slovenian Test accuracy |
|
value: 77.4 |
|
- type: accuracy |
|
name: Guajajara Test accuracy |
|
value: 35.8 |
|
- type: accuracy |
|
name: Kurmanji Test accuracy |
|
value: 77.7 |
|
- type: accuracy |
|
name: Turkish Test accuracy |
|
value: 76.9 |
|
- type: accuracy |
|
name: Finnish Test accuracy |
|
value: 84.9 |
|
- type: accuracy |
|
name: Indonesian Test accuracy |
|
value: 82.0 |
|
- type: accuracy |
|
name: Ukrainian Test accuracy |
|
value: 87.8 |
|
- type: accuracy |
|
name: Polish Test accuracy |
|
value: 88.0 |
|
- type: accuracy |
|
name: Portuguese Test accuracy |
|
value: 82.3 |
|
- type: accuracy |
|
name: Kazakh Test accuracy |
|
value: 83.2 |
|
- type: accuracy |
|
name: Latin Test accuracy |
|
value: 92.9 |
|
- type: accuracy |
|
name: Old French Test accuracy |
|
value: 61.2 |
|
- type: accuracy |
|
name: Buryat Test accuracy |
|
value: 64.7 |
|
- type: accuracy |
|
name: Kaapor Test accuracy |
|
value: 34.2 |
|
- type: accuracy |
|
name: Korean Test accuracy |
|
value: 63.0 |
|
- type: accuracy |
|
name: Estonian Test accuracy |
|
value: 85.5 |
|
- type: accuracy |
|
name: Croatian Test accuracy |
|
value: 86.3 |
|
- type: accuracy |
|
name: Gothic Test accuracy |
|
value: 36.5 |
|
- type: accuracy |
|
name: Swiss German Test accuracy |
|
value: 47.8 |
|
- type: accuracy |
|
name: Assyrian Test accuracy |
|
value: 15.5 |
|
- type: accuracy |
|
name: North Sami Test accuracy |
|
value: 41.4 |
|
- type: accuracy |
|
name: Naija Test accuracy |
|
value: 41.9 |
|
- type: accuracy |
|
name: Latvian Test accuracy |
|
value: 89.1 |
|
- type: accuracy |
|
name: Chinese Test accuracy |
|
value: 44.3 |
|
- type: accuracy |
|
name: Tagalog Test accuracy |
|
value: 73.7 |
|
- type: accuracy |
|
name: Bambara Test accuracy |
|
value: 27.9 |
|
- type: accuracy |
|
name: Lithuanian Test accuracy |
|
value: 88.3 |
|
- type: accuracy |
|
name: Galician Test accuracy |
|
value: 81.7 |
|
- type: accuracy |
|
name: Vietnamese Test accuracy |
|
value: 68.0 |
|
- type: accuracy |
|
name: Greek Test accuracy |
|
value: 74.9 |
|
- type: accuracy |
|
name: Catalan Test accuracy |
|
value: 76.2 |
|
- type: accuracy |
|
name: Czech Test accuracy |
|
value: 86.3 |
|
- type: accuracy |
|
name: Erzya Test accuracy |
|
value: 50.8 |
|
- type: accuracy |
|
name: Bhojpuri Test accuracy |
|
value: 52.5 |
|
- type: accuracy |
|
name: Thai Test accuracy |
|
value: 61.6 |
|
- type: accuracy |
|
name: Marathi Test accuracy |
|
value: 88.3 |
|
- type: accuracy |
|
name: Basque Test accuracy |
|
value: 79.0 |
|
- type: accuracy |
|
name: Slovak Test accuracy |
|
value: 85.9 |
|
- type: accuracy |
|
name: Kiche Test accuracy |
|
value: 39.3 |
|
- type: accuracy |
|
name: Yoruba Test accuracy |
|
value: 29.9 |
|
- type: accuracy |
|
name: Warlpiri Test accuracy |
|
value: 40.9 |
|
- type: accuracy |
|
name: Tamil Test accuracy |
|
value: 85.7 |
|
- type: accuracy |
|
name: Maltese Test accuracy |
|
value: 32.8 |
|
- type: accuracy |
|
name: Ancient Greek Test accuracy |
|
value: 70.5 |
|
- type: accuracy |
|
name: Icelandic Test accuracy |
|
value: 81.6 |
|
- type: accuracy |
|
name: Mbya Guarani Test accuracy |
|
value: 33.1 |
|
- type: accuracy |
|
name: Urdu Test accuracy |
|
value: 61.3 |
|
- type: accuracy |
|
name: Romanian Test accuracy |
|
value: 83.1 |
|
- type: accuracy |
|
name: Persian Test accuracy |
|
value: 75.7 |
|
- type: accuracy |
|
name: Apurina Test accuracy |
|
value: 43.5 |
|
- type: accuracy |
|
name: Japanese Test accuracy |
|
value: 36.5 |
|
- type: accuracy |
|
name: Hungarian Test accuracy |
|
value: 74.5 |
|
- type: accuracy |
|
name: Hindi Test accuracy |
|
value: 67.0 |
|
- type: accuracy |
|
name: Classical Chinese Test accuracy |
|
value: 38.2 |
|
- type: accuracy |
|
name: Komi Permyak Test accuracy |
|
value: 52.2 |
|
- type: accuracy |
|
name: Faroese Test accuracy |
|
value: 75.6 |
|
- type: accuracy |
|
name: Sanskrit Test accuracy |
|
value: 43.5 |
|
- type: accuracy |
|
name: Livvi Test accuracy |
|
value: 66.1 |
|
- type: accuracy |
|
name: Arabic Test accuracy |
|
value: 81.3 |
|
- type: accuracy |
|
name: Wolof Test accuracy |
|
value: 39.1 |
|
- type: accuracy |
|
name: Bulgarian Test accuracy |
|
value: 87.7 |
|
- type: accuracy |
|
name: Akuntsu Test accuracy |
|
value: 35.5 |
|
- type: accuracy |
|
name: Makurap Test accuracy |
|
value: 28.8 |
|
- type: accuracy |
|
name: Kangri Test accuracy |
|
value: 49.8 |
|
- type: accuracy |
|
name: Breton Test accuracy |
|
value: 59.8 |
|
- type: accuracy |
|
name: Telugu Test accuracy |
|
value: 84.3 |
|
- type: accuracy |
|
name: Cantonese Test accuracy |
|
value: 50.3 |
|
- type: accuracy |
|
name: Old Church Slavonic Test accuracy |
|
value: 55.7 |
|
- type: accuracy |
|
name: Karelian Test accuracy |
|
value: 73.0 |
|
- type: accuracy |
|
name: Upper Sorbian Test accuracy |
|
value: 76.0 |
|
- type: accuracy |
|
name: South Levantine Arabic Test accuracy |
|
value: 68.8 |
|
- type: accuracy |
|
name: Komi Zyrian Test accuracy |
|
value: 46.3 |
|
- type: accuracy |
|
name: Irish Test accuracy |
|
value: 64.1 |
|
- type: accuracy |
|
name: Nayini Test accuracy |
|
value: 44.9 |
|
- type: accuracy |
|
name: Munduruku Test accuracy |
|
value: 24.1 |
|
- type: accuracy |
|
name: Manx Test accuracy |
|
value: 39.3 |
|
- type: accuracy |
|
name: Skolt Sami Test accuracy |
|
value: 43.5 |
|
- type: accuracy |
|
name: Afrikaans Test accuracy |
|
value: 74.8 |
|
- type: accuracy |
|
name: Old Turkish Test accuracy |
|
value: 37.1 |
|
- type: accuracy |
|
name: Tupinamba Test accuracy |
|
value: 45.2 |
|
- type: accuracy |
|
name: Belarusian Test accuracy |
|
value: 89.1 |
|
- type: accuracy |
|
name: Serbian Test accuracy |
|
value: 87.2 |
|
- type: accuracy |
|
name: Moksha Test accuracy |
|
value: 47.3 |
|
- type: accuracy |
|
name: Western Armenian Test accuracy |
|
value: 81.6 |
|
- type: accuracy |
|
name: Scottish Gaelic Test accuracy |
|
value: 55.3 |
|
- type: accuracy |
|
name: Khunsari Test accuracy |
|
value: 43.2 |
|
- type: accuracy |
|
name: Hebrew Test accuracy |
|
value: 89.6 |
|
- type: accuracy |
|
name: Uyghur Test accuracy |
|
value: 76.8 |
|
- type: accuracy |
|
name: Chukchi Test accuracy |
|
value: 36.3 |
|
--- |
|
|
|
# XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Latin |
|
|
|
This model is part of our paper called: |
|
|
|
- Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages |
|
|
|
Check the [Space](https://huggingface.co/spaces/wietsedv/xpos) for more details. |
|
|
|
## Usage |
|
```python |
|
from transformers import AutoTokenizer, AutoModelForTokenClassification |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-la") |
|
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-la") |
|
``` |
|
|
