wietsedv's picture
update README
6a4a468
metadata
language:
  - vi
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-vi
    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: 57.2
          - type: accuracy
            name: Dutch Test accuracy
            value: 58.4
          - type: accuracy
            name: German Test accuracy
            value: 57.7
          - type: accuracy
            name: Italian Test accuracy
            value: 57.3
          - type: accuracy
            name: French Test accuracy
            value: 53.8
          - type: accuracy
            name: Spanish Test accuracy
            value: 58.7
          - type: accuracy
            name: Russian Test accuracy
            value: 66.9
          - type: accuracy
            name: Swedish Test accuracy
            value: 59.3
          - type: accuracy
            name: Norwegian Test accuracy
            value: 56.7
          - type: accuracy
            name: Danish Test accuracy
            value: 59.3
          - type: accuracy
            name: Low Saxon Test accuracy
            value: 40.3
          - type: accuracy
            name: Akkadian Test accuracy
            value: 34
          - type: accuracy
            name: Armenian Test accuracy
            value: 62.9
          - type: accuracy
            name: Welsh Test accuracy
            value: 50.9
          - type: accuracy
            name: Old East Slavic Test accuracy
            value: 54.9
          - type: accuracy
            name: Albanian Test accuracy
            value: 57
          - type: accuracy
            name: Slovenian Test accuracy
            value: 53.5
          - type: accuracy
            name: Guajajara Test accuracy
            value: 36.6
          - type: accuracy
            name: Kurmanji Test accuracy
            value: 58.5
          - type: accuracy
            name: Turkish Test accuracy
            value: 61.7
          - type: accuracy
            name: Finnish Test accuracy
            value: 60.2
          - type: accuracy
            name: Indonesian Test accuracy
            value: 62.7
          - type: accuracy
            name: Ukrainian Test accuracy
            value: 66.1
          - type: accuracy
            name: Polish Test accuracy
            value: 65.1
          - type: accuracy
            name: Portuguese Test accuracy
            value: 64.5
          - type: accuracy
            name: Kazakh Test accuracy
            value: 70.5
          - type: accuracy
            name: Latin Test accuracy
            value: 57.3
          - type: accuracy
            name: Old French Test accuracy
            value: 36.4
          - type: accuracy
            name: Buryat Test accuracy
            value: 55.9
          - type: accuracy
            name: Kaapor Test accuracy
            value: 27.9
          - type: accuracy
            name: Korean Test accuracy
            value: 53.4
          - type: accuracy
            name: Estonian Test accuracy
            value: 57.4
          - type: accuracy
            name: Croatian Test accuracy
            value: 59.3
          - type: accuracy
            name: Gothic Test accuracy
            value: 22.2
          - type: accuracy
            name: Swiss German Test accuracy
            value: 39.8
          - type: accuracy
            name: Assyrian Test accuracy
            value: 16.1
          - type: accuracy
            name: North Sami Test accuracy
            value: 38.4
          - type: accuracy
            name: Naija Test accuracy
            value: 26.3
          - type: accuracy
            name: Latvian Test accuracy
            value: 66
          - type: accuracy
            name: Chinese Test accuracy
            value: 35
          - type: accuracy
            name: Tagalog Test accuracy
            value: 63.4
          - type: accuracy
            name: Bambara Test accuracy
            value: 27.8
          - type: accuracy
            name: Lithuanian Test accuracy
            value: 68.2
          - type: accuracy
            name: Galician Test accuracy
            value: 60.6
          - type: accuracy
            name: Vietnamese Test accuracy
            value: 93.7
          - type: accuracy
            name: Greek Test accuracy
            value: 54.1
          - type: accuracy
            name: Catalan Test accuracy
            value: 55
          - type: accuracy
            name: Czech Test accuracy
            value: 62.2
          - type: accuracy
            name: Erzya Test accuracy
            value: 48.8
          - type: accuracy
            name: Bhojpuri Test accuracy
            value: 44.4
          - type: accuracy
            name: Thai Test accuracy
            value: 50.2
          - type: accuracy
            name: Marathi Test accuracy
            value: 66.3
          - type: accuracy
            name: Basque Test accuracy
            value: 59.2
          - type: accuracy
            name: Slovak Test accuracy
            value: 63.1
          - type: accuracy
            name: Kiche Test accuracy
            value: 38.7
          - type: accuracy
            name: Yoruba Test accuracy
            value: 25.3
          - type: accuracy
            name: Warlpiri Test accuracy
            value: 49
          - type: accuracy
            name: Tamil Test accuracy
            value: 62.8
          - type: accuracy
            name: Maltese Test accuracy
            value: 31.6
          - type: accuracy
            name: Ancient Greek Test accuracy
            value: 44.9
          - type: accuracy
            name: Icelandic Test accuracy
            value: 52.2
          - type: accuracy
            name: Mbya Guarani Test accuracy
            value: 33.5
          - type: accuracy
            name: Urdu Test accuracy
            value: 45.2
          - type: accuracy
            name: Romanian Test accuracy
            value: 61.8
          - type: accuracy
            name: Persian Test accuracy
            value: 57.3
          - type: accuracy
            name: Apurina Test accuracy
            value: 46.2
          - type: accuracy
            name: Japanese Test accuracy
            value: 25.5
          - type: accuracy
            name: Hungarian Test accuracy
            value: 55.5
          - type: accuracy
            name: Hindi Test accuracy
            value: 49.6
          - type: accuracy
            name: Classical Chinese Test accuracy
            value: 22.4
          - type: accuracy
            name: Komi Permyak Test accuracy
            value: 44.9
          - type: accuracy
            name: Faroese Test accuracy
            value: 58.4
          - type: accuracy
            name: Sanskrit Test accuracy
            value: 34.7
          - type: accuracy
            name: Livvi Test accuracy
            value: 60.3
          - type: accuracy
            name: Arabic Test accuracy
            value: 61.6
          - type: accuracy
            name: Wolof Test accuracy
            value: 28.9
          - type: accuracy
            name: Bulgarian Test accuracy
            value: 64
          - type: accuracy
            name: Akuntsu Test accuracy
            value: 43.4
          - type: accuracy
            name: Makurap Test accuracy
            value: 20.5
          - type: accuracy
            name: Kangri Test accuracy
            value: 40.7
          - type: accuracy
            name: Breton Test accuracy
            value: 53
          - type: accuracy
            name: Telugu Test accuracy
            value: 64.6
          - type: accuracy
            name: Cantonese Test accuracy
            value: 40.7
          - type: accuracy
            name: Old Church Slavonic Test accuracy
            value: 36.4
          - type: accuracy
            name: Karelian Test accuracy
            value: 57.7
          - type: accuracy
            name: Upper Sorbian Test accuracy
            value: 58
          - type: accuracy
            name: South Levantine Arabic Test accuracy
            value: 59.7
          - type: accuracy
            name: Komi Zyrian Test accuracy
            value: 46.3
          - type: accuracy
            name: Irish Test accuracy
            value: 48.9
          - type: accuracy
            name: Nayini Test accuracy
            value: 42.3
          - type: accuracy
            name: Munduruku Test accuracy
            value: 38.1
          - type: accuracy
            name: Manx Test accuracy
            value: 35.2
          - type: accuracy
            name: Skolt Sami Test accuracy
            value: 39.3
          - type: accuracy
            name: Afrikaans Test accuracy
            value: 53.8
          - type: accuracy
            name: Old Turkish Test accuracy
            value: 37.1
          - type: accuracy
            name: Tupinamba Test accuracy
            value: 49.1
          - type: accuracy
            name: Belarusian Test accuracy
            value: 66.3
          - type: accuracy
            name: Serbian Test accuracy
            value: 58.3
          - type: accuracy
            name: Moksha Test accuracy
            value: 46.6
          - type: accuracy
            name: Western Armenian Test accuracy
            value: 58.2
          - type: accuracy
            name: Scottish Gaelic Test accuracy
            value: 43.8
          - type: accuracy
            name: Khunsari Test accuracy
            value: 45.9
          - type: accuracy
            name: Hebrew Test accuracy
            value: 75
          - type: accuracy
            name: Uyghur Test accuracy
            value: 70.7
          - type: accuracy
            name: Chukchi Test accuracy
            value: 33.1

XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Vietnamese

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-vi")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-vi")