--- language: - pcm 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-pcm 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: 77.2 - type: accuracy name: Dutch Test accuracy value: 75.2 - type: accuracy name: German Test accuracy value: 73.2 - type: accuracy name: Italian Test accuracy value: 68.9 - type: accuracy name: French Test accuracy value: 74.0 - type: accuracy name: Spanish Test accuracy value: 75.1 - type: accuracy name: Russian Test accuracy value: 70.3 - type: accuracy name: Swedish Test accuracy value: 78.9 - type: accuracy name: Norwegian Test accuracy value: 74.3 - type: accuracy name: Danish Test accuracy value: 73.4 - type: accuracy name: Low Saxon Test accuracy value: 37.9 - type: accuracy name: Akkadian Test accuracy value: 28.0 - type: accuracy name: Armenian Test accuracy value: 65.4 - type: accuracy name: Welsh Test accuracy value: 59.7 - type: accuracy name: Old East Slavic Test accuracy value: 61.0 - type: accuracy name: Albanian Test accuracy value: 66.1 - type: accuracy name: Slovenian Test accuracy value: 67.6 - type: accuracy name: Guajajara Test accuracy value: 16.1 - type: accuracy name: Kurmanji Test accuracy value: 54.8 - type: accuracy name: Turkish Test accuracy value: 58.2 - type: accuracy name: Finnish Test accuracy value: 67.4 - type: accuracy name: Indonesian Test accuracy value: 68.5 - type: accuracy name: Ukrainian Test accuracy value: 68.1 - type: accuracy name: Polish Test accuracy value: 68.8 - type: accuracy name: Portuguese Test accuracy value: 72.9 - type: accuracy name: Kazakh Test accuracy value: 60.1 - type: accuracy name: Latin Test accuracy value: 64.3 - type: accuracy name: Old French Test accuracy value: 51.1 - type: accuracy name: Buryat Test accuracy value: 38.9 - type: accuracy name: Kaapor Test accuracy value: 16.7 - type: accuracy name: Korean Test accuracy value: 52.4 - type: accuracy name: Estonian Test accuracy value: 68.3 - type: accuracy name: Croatian Test accuracy value: 73.0 - type: accuracy name: Gothic Test accuracy value: 21.4 - type: accuracy name: Swiss German Test accuracy value: 33.4 - type: accuracy name: Assyrian Test accuracy value: 0.0 - type: accuracy name: North Sami Test accuracy value: 24.3 - type: accuracy name: Naija Test accuracy value: 97.9 - type: accuracy name: Latvian Test accuracy value: 66.3 - type: accuracy name: Chinese Test accuracy value: 34.3 - type: accuracy name: Tagalog Test accuracy value: 49.9 - type: accuracy name: Bambara Test accuracy value: 16.7 - type: accuracy name: Lithuanian Test accuracy value: 65.7 - type: accuracy name: Galician Test accuracy value: 72.4 - type: accuracy name: Vietnamese Test accuracy value: 54.3 - type: accuracy name: Greek Test accuracy value: 73.3 - type: accuracy name: Catalan Test accuracy value: 73.6 - type: accuracy name: Czech Test accuracy value: 69.5 - type: accuracy name: Erzya Test accuracy value: 22.1 - type: accuracy name: Bhojpuri Test accuracy value: 36.6 - type: accuracy name: Thai Test accuracy value: 65.4 - type: accuracy name: Marathi Test accuracy value: 50.3 - type: accuracy name: Basque Test accuracy value: 58.5 - type: accuracy name: Slovak Test accuracy value: 70.4 - type: accuracy name: Kiche Test accuracy value: 8.0 - type: accuracy name: Yoruba Test accuracy value: 6.1 - type: accuracy name: Warlpiri Test accuracy value: 15.4 - type: accuracy name: Tamil Test accuracy value: 60.1 - type: accuracy name: Maltese Test accuracy value: 12.2 - type: accuracy name: Ancient Greek Test accuracy value: 45.8 - type: accuracy name: Icelandic Test accuracy value: 72.5 - type: accuracy name: Mbya Guarani Test accuracy value: 11.4 - type: accuracy name: Urdu Test accuracy value: 59.1 - type: accuracy name: Romanian Test accuracy value: 64.8 - type: accuracy name: Persian Test accuracy value: 67.2 - type: accuracy name: Apurina Test accuracy value: 15.5 - type: accuracy name: Japanese Test accuracy value: 26.1 - type: accuracy name: Hungarian Test accuracy value: 68.6 - type: accuracy name: Hindi Test accuracy value: 65.0 - type: accuracy name: Classical Chinese Test accuracy value: 30.4 - type: accuracy name: Komi Permyak Test accuracy value: 21.2 - type: accuracy name: Faroese Test accuracy value: 61.6 - type: accuracy name: Sanskrit Test accuracy value: 25.6 - type: accuracy name: Livvi Test accuracy value: 39.7 - type: accuracy name: Arabic Test accuracy value: 63.5 - type: accuracy name: Wolof Test accuracy value: 15.9 - type: accuracy name: Bulgarian Test accuracy value: 74.6 - type: accuracy name: Akuntsu Test accuracy value: 26.5 - type: accuracy name: Makurap Test accuracy value: 11.6 - type: accuracy name: Kangri Test accuracy value: 27.8 - type: accuracy name: Breton Test accuracy value: 46.6 - type: accuracy name: Telugu Test accuracy value: 59.4 - type: accuracy name: Cantonese Test accuracy value: 30.7 - type: accuracy name: Old Church Slavonic Test accuracy value: 36.7 - type: accuracy name: Karelian Test accuracy value: 45.9 - type: accuracy name: Upper Sorbian Test accuracy value: 49.3 - type: accuracy name: South Levantine Arabic Test accuracy value: 42.5 - type: accuracy name: Komi Zyrian Test accuracy value: 18.4 - type: accuracy name: Irish Test accuracy value: 48.3 - type: accuracy name: Nayini Test accuracy value: 24.4 - type: accuracy name: Munduruku Test accuracy value: 16.1 - type: accuracy name: Manx Test accuracy value: 14.7 - type: accuracy name: Skolt Sami Test accuracy value: 5.4 - type: accuracy name: Afrikaans Test accuracy value: 76.5 - type: accuracy name: Old Turkish Test accuracy value: 0.0 - type: accuracy name: Tupinamba Test accuracy value: 16.3 - type: accuracy name: Belarusian Test accuracy value: 70.7 - type: accuracy name: Serbian Test accuracy value: 74.8 - type: accuracy name: Moksha Test accuracy value: 24.1 - type: accuracy name: Western Armenian Test accuracy value: 59.8 - type: accuracy name: Scottish Gaelic Test accuracy value: 45.4 - type: accuracy name: Khunsari Test accuracy value: 21.6 - type: accuracy name: Hebrew Test accuracy value: 65.6 - type: accuracy name: Uyghur Test accuracy value: 55.0 - type: accuracy name: Chukchi Test accuracy value: 12.6 --- # XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Naija 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-pcm") model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-pcm") ```