language:
- en 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-en
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: 96.0
- type: accuracy name: Dutch Test accuracy value: 90.4
- type: accuracy name: German Test accuracy value: 88.6
- type: accuracy name: Italian Test accuracy value: 87.8
- type: accuracy name: French Test accuracy value: 87.4
- type: accuracy name: Spanish Test accuracy value: 90.3
- type: accuracy name: Russian Test accuracy value: 91.0
- type: accuracy name: Swedish Test accuracy value: 94.0
- type: accuracy name: Norwegian Test accuracy value: 89.6
- type: accuracy name: Danish Test accuracy value: 91.6
- type: accuracy name: Low Saxon Test accuracy value: 57.4
- type: accuracy name: Akkadian Test accuracy value: 26.4
- type: accuracy name: Armenian Test accuracy value: 88.5
- type: accuracy name: Welsh Test accuracy value: 70.6
- type: accuracy name: Old East Slavic Test accuracy value: 76.5
- type: accuracy name: Albanian Test accuracy value: 82.3
- type: accuracy name: Slovenian Test accuracy value: 79.0
- type: accuracy name: Guajajara Test accuracy value: 17.2
- type: accuracy name: Kurmanji Test accuracy value: 76.9
- type: accuracy name: Turkish Test accuracy value: 79.1
- type: accuracy name: Finnish Test accuracy value: 87.2
- type: accuracy name: Indonesian Test accuracy value: 86.9
- type: accuracy name: Ukrainian Test accuracy value: 87.6
- type: accuracy name: Polish Test accuracy value: 87.2
- type: accuracy name: Portuguese Test accuracy value: 90.0
- type: accuracy name: Kazakh Test accuracy value: 82.5
- type: accuracy name: Latin Test accuracy value: 79.6
- type: accuracy name: Old French Test accuracy value: 53.4
- type: accuracy name: Buryat Test accuracy value: 58.8
- type: accuracy name: Kaapor Test accuracy value: 9.2
- type: accuracy name: Korean Test accuracy value: 64.0
- type: accuracy name: Estonian Test accuracy value: 88.4
- type: accuracy name: Croatian Test accuracy value: 87.9
- type: accuracy name: Gothic Test accuracy value: 20.5
- type: accuracy name: Swiss German Test accuracy value: 47.6
- type: accuracy name: Assyrian Test accuracy value: 14.6
- type: accuracy name: North Sami Test accuracy value: 32.0
- type: accuracy name: Naija Test accuracy value: 47.5
- type: accuracy name: Latvian Test accuracy value: 87.5
- type: accuracy name: Chinese Test accuracy value: 47.5
- type: accuracy name: Tagalog Test accuracy value: 73.5
- type: accuracy name: Bambara Test accuracy value: 27.7
- type: accuracy name: Lithuanian Test accuracy value: 87.3
- type: accuracy name: Galician Test accuracy value: 87.1
- type: accuracy name: Vietnamese Test accuracy value: 66.4
- type: accuracy name: Greek Test accuracy value: 87.6
- type: accuracy name: Catalan Test accuracy value: 89.7
- type: accuracy name: Czech Test accuracy value: 88.1
- type: accuracy name: Erzya Test accuracy value: 47.6
- type: accuracy name: Bhojpuri Test accuracy value: 50.7
- type: accuracy name: Thai Test accuracy value: 59.5
- type: accuracy name: Marathi Test accuracy value: 82.2
- type: accuracy name: Basque Test accuracy value: 76.0
- type: accuracy name: Slovak Test accuracy value: 88.5
- type: accuracy name: Kiche Test accuracy value: 25.4
- type: accuracy name: Yoruba Test accuracy value: 18.5
- type: accuracy name: Warlpiri Test accuracy value: 29.1
- type: accuracy name: Tamil Test accuracy value: 83.4
- type: accuracy name: Maltese Test accuracy value: 21.1
- type: accuracy name: Ancient Greek Test accuracy value: 66.8
- type: accuracy name: Icelandic Test accuracy value: 84.8
- type: accuracy name: Mbya Guarani Test accuracy value: 24.1
- type: accuracy name: Urdu Test accuracy value: 67.0
- type: accuracy name: Romanian Test accuracy value: 85.7
- type: accuracy name: Persian Test accuracy value: 76.7
- type: accuracy name: Apurina Test accuracy value: 28.6
- type: accuracy name: Japanese Test accuracy value: 34.1
- type: accuracy name: Hungarian Test accuracy value: 86.0
- type: accuracy name: Hindi Test accuracy value: 74.1
- type: accuracy name: Classical Chinese Test accuracy value: 29.4
- type: accuracy name: Komi Permyak Test accuracy value: 47.4
- type: accuracy name: Faroese Test accuracy value: 77.0
- type: accuracy name: Sanskrit Test accuracy value: 25.6
- type: accuracy name: Livvi Test accuracy value: 63.2
- type: accuracy name: Arabic Test accuracy value: 80.7
- type: accuracy name: Wolof Test accuracy value: 26.1
- type: accuracy name: Bulgarian Test accuracy value: 90.8
- type: accuracy name: Akuntsu Test accuracy value: 18.3
- type: accuracy name: Makurap Test accuracy value: 5.5
- type: accuracy name: Kangri Test accuracy value: 43.0
- type: accuracy name: Breton Test accuracy value: 64.1
- type: accuracy name: Telugu Test accuracy value: 84.7
- type: accuracy name: Cantonese Test accuracy value: 54.0
- type: accuracy name: Old Church Slavonic Test accuracy value: 53.7
- type: accuracy name: Karelian Test accuracy value: 69.7
- type: accuracy name: Upper Sorbian Test accuracy value: 75.6
- type: accuracy name: South Levantine Arabic Test accuracy value: 66.3
- type: accuracy name: Komi Zyrian Test accuracy value: 39.9
- type: accuracy name: Irish Test accuracy value: 67.0
- type: accuracy name: Nayini Test accuracy value: 44.9
- type: accuracy name: Munduruku Test accuracy value: 12.3
- type: accuracy name: Manx Test accuracy value: 25.4
- type: accuracy name: Skolt Sami Test accuracy value: 29.9
- type: accuracy name: Afrikaans Test accuracy value: 89.3
- type: accuracy name: Old Turkish Test accuracy value: 37.1
- type: accuracy name: Tupinamba Test accuracy value: 23.1
- type: accuracy name: Belarusian Test accuracy value: 89.1
- type: accuracy name: Serbian Test accuracy value: 88.4
- type: accuracy name: Moksha Test accuracy value: 44.1
- type: accuracy name: Western Armenian Test accuracy value: 80.1
- type: accuracy name: Scottish Gaelic Test accuracy value: 59.0
- type: accuracy name: Khunsari Test accuracy value: 43.2
- type: accuracy name: Hebrew Test accuracy value: 90.6
- type: accuracy name: Uyghur Test accuracy value: 75.8
- type: accuracy name: Chukchi Test accuracy value: 32.6
- task:
type: token-classification
name: Part-of-Speech Tagging
dataset:
type: universal_dependencies
name: Universal Dependencies v2.8
metrics:
XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: English
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 for more details.
Usage
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-en")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-en")