metadata
language:
- fr
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-fr
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: 87.6
- type: accuracy
name: Dutch Test accuracy
value: 89
- type: accuracy
name: German Test accuracy
value: 85.5
- type: accuracy
name: Italian Test accuracy
value: 91.7
- type: accuracy
name: French Test accuracy
value: 97.1
- type: accuracy
name: Spanish Test accuracy
value: 93.4
- type: accuracy
name: Russian Test accuracy
value: 91.4
- type: accuracy
name: Swedish Test accuracy
value: 89.6
- type: accuracy
name: Norwegian Test accuracy
value: 84.3
- type: accuracy
name: Danish Test accuracy
value: 90.2
- type: accuracy
name: Low Saxon Test accuracy
value: 32.4
- type: accuracy
name: Akkadian Test accuracy
value: 24.5
- type: accuracy
name: Armenian Test accuracy
value: 87.2
- type: accuracy
name: Welsh Test accuracy
value: 69.2
- type: accuracy
name: Old East Slavic Test accuracy
value: 71.5
- type: accuracy
name: Albanian Test accuracy
value: 78.3
- type: accuracy
name: Slovenian Test accuracy
value: 80.6
- type: accuracy
name: Guajajara Test accuracy
value: 20.3
- type: accuracy
name: Kurmanji Test accuracy
value: 78.9
- type: accuracy
name: Turkish Test accuracy
value: 77.9
- type: accuracy
name: Finnish Test accuracy
value: 86.5
- type: accuracy
name: Indonesian Test accuracy
value: 84.8
- type: accuracy
name: Ukrainian Test accuracy
value: 88.9
- type: accuracy
name: Polish Test accuracy
value: 88.1
- type: accuracy
name: Portuguese Test accuracy
value: 92.3
- type: accuracy
name: Kazakh Test accuracy
value: 82.9
- type: accuracy
name: Latin Test accuracy
value: 79.6
- type: accuracy
name: Old French Test accuracy
value: 68.2
- type: accuracy
name: Buryat Test accuracy
value: 53.6
- type: accuracy
name: Kaapor Test accuracy
value: 15
- type: accuracy
name: Korean Test accuracy
value: 64.3
- type: accuracy
name: Estonian Test accuracy
value: 87.5
- type: accuracy
name: Croatian Test accuracy
value: 89.5
- type: accuracy
name: Gothic Test accuracy
value: 11.6
- type: accuracy
name: Swiss German Test accuracy
value: 39.5
- type: accuracy
name: Assyrian Test accuracy
value: 14.8
- type: accuracy
name: North Sami Test accuracy
value: 27
- type: accuracy
name: Naija Test accuracy
value: 36.9
- type: accuracy
name: Latvian Test accuracy
value: 87.7
- type: accuracy
name: Chinese Test accuracy
value: 44.1
- type: accuracy
name: Tagalog Test accuracy
value: 72.8
- type: accuracy
name: Bambara Test accuracy
value: 24.7
- type: accuracy
name: Lithuanian Test accuracy
value: 86.9
- type: accuracy
name: Galician Test accuracy
value: 91.6
- type: accuracy
name: Vietnamese Test accuracy
value: 67
- type: accuracy
name: Greek Test accuracy
value: 88
- type: accuracy
name: Catalan Test accuracy
value: 92.5
- type: accuracy
name: Czech Test accuracy
value: 89.7
- type: accuracy
name: Erzya Test accuracy
value: 41.2
- type: accuracy
name: Bhojpuri Test accuracy
value: 48.9
- type: accuracy
name: Thai Test accuracy
value: 56.3
- type: accuracy
name: Marathi Test accuracy
value: 83.4
- type: accuracy
name: Basque Test accuracy
value: 75.9
- type: accuracy
name: Slovak Test accuracy
value: 91.1
- type: accuracy
name: Kiche Test accuracy
value: 32.5
- type: accuracy
name: Yoruba Test accuracy
value: 19.4
- type: accuracy
name: Warlpiri Test accuracy
value: 26.3
- type: accuracy
name: Tamil Test accuracy
value: 83.5
- type: accuracy
name: Maltese Test accuracy
value: 17.4
- type: accuracy
name: Ancient Greek Test accuracy
value: 60.2
- type: accuracy
name: Icelandic Test accuracy
value: 83.2
- type: accuracy
name: Mbya Guarani Test accuracy
value: 26.1
- type: accuracy
name: Urdu Test accuracy
value: 67.5
- type: accuracy
name: Romanian Test accuracy
value: 87.1
- type: accuracy
name: Persian Test accuracy
value: 78.6
- type: accuracy
name: Apurina Test accuracy
value: 26.1
- type: accuracy
name: Japanese Test accuracy
value: 32.3
- type: accuracy
name: Hungarian Test accuracy
value: 86.3
- type: accuracy
name: Hindi Test accuracy
value: 73.7
- type: accuracy
name: Classical Chinese Test accuracy
value: 28.4
- type: accuracy
name: Komi Permyak Test accuracy
value: 35
- type: accuracy
name: Faroese Test accuracy
value: 75.7
- type: accuracy
name: Sanskrit Test accuracy
value: 17.9
- type: accuracy
name: Livvi Test accuracy
value: 53.2
- type: accuracy
name: Arabic Test accuracy
value: 83.1
- type: accuracy
name: Wolof Test accuracy
value: 24.6
- type: accuracy
name: Bulgarian Test accuracy
value: 90.9
- type: accuracy
name: Akuntsu Test accuracy
value: 35.2
- type: accuracy
name: Makurap Test accuracy
value: 13
- type: accuracy
name: Kangri Test accuracy
value: 43
- type: accuracy
name: Breton Test accuracy
value: 67.7
- type: accuracy
name: Telugu Test accuracy
value: 83.6
- type: accuracy
name: Cantonese Test accuracy
value: 51.6
- type: accuracy
name: Old Church Slavonic Test accuracy
value: 43.3
- type: accuracy
name: Karelian Test accuracy
value: 67.3
- type: accuracy
name: Upper Sorbian Test accuracy
value: 65.1
- type: accuracy
name: South Levantine Arabic Test accuracy
value: 69.3
- type: accuracy
name: Komi Zyrian Test accuracy
value: 29.5
- type: accuracy
name: Irish Test accuracy
value: 69.4
- type: accuracy
name: Nayini Test accuracy
value: 48.7
- type: accuracy
name: Munduruku Test accuracy
value: 19.9
- type: accuracy
name: Manx Test accuracy
value: 27.6
- type: accuracy
name: Skolt Sami Test accuracy
value: 26.9
- type: accuracy
name: Afrikaans Test accuracy
value: 84.9
- type: accuracy
name: Old Turkish Test accuracy
value: 38
- type: accuracy
name: Tupinamba Test accuracy
value: 22.8
- type: accuracy
name: Belarusian Test accuracy
value: 89.5
- type: accuracy
name: Serbian Test accuracy
value: 90.8
- type: accuracy
name: Moksha Test accuracy
value: 39
- type: accuracy
name: Western Armenian Test accuracy
value: 76.8
- type: accuracy
name: Scottish Gaelic Test accuracy
value: 60
- type: accuracy
name: Khunsari Test accuracy
value: 35.1
- type: accuracy
name: Hebrew Test accuracy
value: 94.8
- type: accuracy
name: Uyghur Test accuracy
value: 75.2
- type: accuracy
name: Chukchi Test accuracy
value: 30.9
XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: French
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-fr")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-fr")