|
|
| --- |
| language: |
| - is |
| 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-is |
| 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: 88.4 |
| - type: accuracy |
| name: Dutch Test accuracy |
| value: 86.9 |
| - type: accuracy |
| name: German Test accuracy |
| value: 82.7 |
| - type: accuracy |
| name: Italian Test accuracy |
| value: 84.6 |
| - type: accuracy |
| name: French Test accuracy |
| value: 83.6 |
| - type: accuracy |
| name: Spanish Test accuracy |
| value: 83.6 |
| - type: accuracy |
| name: Russian Test accuracy |
| value: 87.6 |
| - type: accuracy |
| name: Swedish Test accuracy |
| value: 89.9 |
| - type: accuracy |
| name: Norwegian Test accuracy |
| value: 86.4 |
| - type: accuracy |
| name: Danish Test accuracy |
| value: 89.6 |
| - type: accuracy |
| name: Low Saxon Test accuracy |
| value: 57.6 |
| - type: accuracy |
| name: Akkadian Test accuracy |
| value: 30.5 |
| - type: accuracy |
| name: Armenian Test accuracy |
| value: 86.6 |
| - type: accuracy |
| name: Welsh Test accuracy |
| value: 66.9 |
| - type: accuracy |
| name: Old East Slavic Test accuracy |
| value: 76.3 |
| - type: accuracy |
| name: Albanian Test accuracy |
| value: 80.8 |
| - type: accuracy |
| name: Slovenian Test accuracy |
| value: 76.8 |
| - type: accuracy |
| name: Guajajara Test accuracy |
| value: 31.8 |
| - type: accuracy |
| name: Kurmanji Test accuracy |
| value: 78.6 |
| - type: accuracy |
| name: Turkish Test accuracy |
| value: 77.3 |
| - type: accuracy |
| name: Finnish Test accuracy |
| value: 84.8 |
| - type: accuracy |
| name: Indonesian Test accuracy |
| value: 84.4 |
| - type: accuracy |
| name: Ukrainian Test accuracy |
| value: 85.9 |
| - type: accuracy |
| name: Polish Test accuracy |
| value: 84.2 |
| - type: accuracy |
| name: Portuguese Test accuracy |
| value: 86.6 |
| - type: accuracy |
| name: Kazakh Test accuracy |
| value: 81.8 |
| - type: accuracy |
| name: Latin Test accuracy |
| value: 75.8 |
| - type: accuracy |
| name: Old French Test accuracy |
| value: 58.6 |
| - type: accuracy |
| name: Buryat Test accuracy |
| value: 63.1 |
| - type: accuracy |
| name: Kaapor Test accuracy |
| value: 18.3 |
| - type: accuracy |
| name: Korean Test accuracy |
| value: 64.3 |
| - type: accuracy |
| name: Estonian Test accuracy |
| value: 86.7 |
| - type: accuracy |
| name: Croatian Test accuracy |
| value: 86.0 |
| - type: accuracy |
| name: Gothic Test accuracy |
| value: 26.6 |
| - type: accuracy |
| name: Swiss German Test accuracy |
| value: 45.6 |
| - type: accuracy |
| name: Assyrian Test accuracy |
| value: 15.5 |
| - type: accuracy |
| name: North Sami Test accuracy |
| value: 43.9 |
| - type: accuracy |
| name: Naija Test accuracy |
| value: 46.6 |
| - type: accuracy |
| name: Latvian Test accuracy |
| value: 85.3 |
| - type: accuracy |
| name: Chinese Test accuracy |
| value: 60.4 |
| - type: accuracy |
| name: Tagalog Test accuracy |
| value: 80.0 |
| - type: accuracy |
| name: Bambara Test accuracy |
| value: 32.5 |
| - type: accuracy |
| name: Lithuanian Test accuracy |
| value: 85.9 |
| - type: accuracy |
| name: Galician Test accuracy |
| value: 80.7 |
| - type: accuracy |
| name: Vietnamese Test accuracy |
| value: 64.1 |
| - type: accuracy |
| name: Greek Test accuracy |
| value: 80.5 |
| - type: accuracy |
| name: Catalan Test accuracy |
| value: 82.7 |
| - type: accuracy |
| name: Czech Test accuracy |
| value: 84.6 |
| - type: accuracy |
| name: Erzya Test accuracy |
| value: 52.8 |
| - type: accuracy |
| name: Bhojpuri Test accuracy |
| value: 59.0 |
| - type: accuracy |
| name: Thai Test accuracy |
| value: 68.2 |
| - type: accuracy |
| name: Marathi Test accuracy |
| value: 87.1 |
| - type: accuracy |
| name: Basque Test accuracy |
| value: 79.5 |
| - type: accuracy |
| name: Slovak Test accuracy |
| value: 86.0 |
| - type: accuracy |
| name: Kiche Test accuracy |
| value: 42.2 |
| - type: accuracy |
| name: Yoruba Test accuracy |
| value: 34.3 |
| - type: accuracy |
| name: Warlpiri Test accuracy |
| value: 43.7 |
| - type: accuracy |
| name: Tamil Test accuracy |
| value: 83.9 |
| - type: accuracy |
| name: Maltese Test accuracy |
| value: 27.5 |
| - type: accuracy |
| name: Ancient Greek Test accuracy |
| value: 64.0 |
| - type: accuracy |
| name: Icelandic Test accuracy |
| value: 95.6 |
| - type: accuracy |
| name: Mbya Guarani Test accuracy |
| value: 31.9 |
| - type: accuracy |
| name: Urdu Test accuracy |
| value: 72.7 |
| - type: accuracy |
| name: Romanian Test accuracy |
| value: 82.0 |
| - type: accuracy |
| name: Persian Test accuracy |
| value: 78.3 |
| - type: accuracy |
| name: Apurina Test accuracy |
| value: 47.9 |
| - type: accuracy |
| name: Japanese Test accuracy |
| value: 44.0 |
| - type: accuracy |
| name: Hungarian Test accuracy |
| value: 77.2 |
| - type: accuracy |
| name: Hindi Test accuracy |
| value: 77.4 |
| - type: accuracy |
| name: Classical Chinese Test accuracy |
| value: 46.0 |
| - type: accuracy |
| name: Komi Permyak Test accuracy |
| value: 52.7 |
| - type: accuracy |
| name: Faroese Test accuracy |
| value: 83.9 |
| - type: accuracy |
| name: Sanskrit Test accuracy |
| value: 37.4 |
| - type: accuracy |
| name: Livvi Test accuracy |
| value: 66.8 |
| - type: accuracy |
| name: Arabic Test accuracy |
| value: 79.2 |
| - type: accuracy |
| name: Wolof Test accuracy |
| value: 39.9 |
| - type: accuracy |
| name: Bulgarian Test accuracy |
| value: 87.7 |
| - type: accuracy |
| name: Akuntsu Test accuracy |
| value: 37.0 |
| - type: accuracy |
| name: Makurap Test accuracy |
| value: 24.7 |
| - type: accuracy |
| name: Kangri Test accuracy |
| value: 50.2 |
| - type: accuracy |
| name: Breton Test accuracy |
| value: 61.8 |
| - type: accuracy |
| name: Telugu Test accuracy |
| value: 84.5 |
| - type: accuracy |
| name: Cantonese Test accuracy |
| value: 60.6 |
| - type: accuracy |
| name: Old Church Slavonic Test accuracy |
| value: 53.9 |
| - type: accuracy |
| name: Karelian Test accuracy |
| value: 74.0 |
| - type: accuracy |
| name: Upper Sorbian Test accuracy |
| value: 75.5 |
| - type: accuracy |
| name: South Levantine Arabic Test accuracy |
| value: 70.8 |
| - type: accuracy |
| name: Komi Zyrian Test accuracy |
| value: 47.1 |
| - type: accuracy |
| name: Irish Test accuracy |
| value: 66.8 |
| - type: accuracy |
| name: Nayini Test accuracy |
| value: 43.6 |
| - type: accuracy |
| name: Munduruku Test accuracy |
| value: 28.3 |
| - type: accuracy |
| name: Manx Test accuracy |
| value: 48.6 |
| - type: accuracy |
| name: Skolt Sami Test accuracy |
| value: 39.6 |
| - type: accuracy |
| name: Afrikaans Test accuracy |
| value: 87.4 |
| - type: accuracy |
| name: Old Turkish Test accuracy |
| value: 38.9 |
| - type: accuracy |
| name: Tupinamba Test accuracy |
| value: 37.6 |
| - type: accuracy |
| name: Belarusian Test accuracy |
| value: 86.8 |
| - type: accuracy |
| name: Serbian Test accuracy |
| value: 87.2 |
| - type: accuracy |
| name: Moksha Test accuracy |
| value: 49.8 |
| - type: accuracy |
| name: Western Armenian Test accuracy |
| value: 79.9 |
| - type: accuracy |
| name: Scottish Gaelic Test accuracy |
| value: 56.8 |
| - type: accuracy |
| name: Khunsari Test accuracy |
| value: 52.7 |
| - type: accuracy |
| name: Hebrew Test accuracy |
| value: 85.4 |
| - type: accuracy |
| name: Uyghur Test accuracy |
| value: 76.9 |
| - type: accuracy |
| name: Chukchi Test accuracy |
| value: 37.7 |
| --- |
| |
| # XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Icelandic |
|
|
| 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-is") |
| model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-is") |
| ``` |
|
|
