--- language: - sa 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-sa 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: 31.4 - type: accuracy name: Dutch Test accuracy value: 28.4 - type: accuracy name: German Test accuracy value: 32.3 - type: accuracy name: Italian Test accuracy value: 28.3 - type: accuracy name: French Test accuracy value: 28.1 - type: accuracy name: Spanish Test accuracy value: 28.5 - type: accuracy name: Russian Test accuracy value: 37.5 - type: accuracy name: Swedish Test accuracy value: 35.7 - type: accuracy name: Norwegian Test accuracy value: 32.0 - type: accuracy name: Danish Test accuracy value: 32.7 - type: accuracy name: Low Saxon Test accuracy value: 28.0 - type: accuracy name: Akkadian Test accuracy value: 26.2 - type: accuracy name: Armenian Test accuracy value: 39.0 - type: accuracy name: Welsh Test accuracy value: 23.9 - type: accuracy name: Old East Slavic Test accuracy value: 36.8 - type: accuracy name: Albanian Test accuracy value: 34.1 - type: accuracy name: Slovenian Test accuracy value: 30.4 - type: accuracy name: Guajajara Test accuracy value: 16.6 - type: accuracy name: Kurmanji Test accuracy value: 34.8 - type: accuracy name: Turkish Test accuracy value: 42.8 - type: accuracy name: Finnish Test accuracy value: 42.5 - type: accuracy name: Indonesian Test accuracy value: 34.5 - type: accuracy name: Ukrainian Test accuracy value: 38.2 - type: accuracy name: Polish Test accuracy value: 36.6 - type: accuracy name: Portuguese Test accuracy value: 30.7 - type: accuracy name: Kazakh Test accuracy value: 44.2 - type: accuracy name: Latin Test accuracy value: 38.1 - type: accuracy name: Old French Test accuracy value: 35.3 - type: accuracy name: Buryat Test accuracy value: 33.0 - type: accuracy name: Kaapor Test accuracy value: 29.2 - type: accuracy name: Korean Test accuracy value: 39.6 - type: accuracy name: Estonian Test accuracy value: 41.1 - type: accuracy name: Croatian Test accuracy value: 34.9 - type: accuracy name: Gothic Test accuracy value: 26.7 - type: accuracy name: Swiss German Test accuracy value: 23.6 - type: accuracy name: Assyrian Test accuracy value: 9.7 - type: accuracy name: North Sami Test accuracy value: 21.7 - type: accuracy name: Naija Test accuracy value: 24.0 - type: accuracy name: Latvian Test accuracy value: 42.3 - type: accuracy name: Chinese Test accuracy value: 29.3 - type: accuracy name: Tagalog Test accuracy value: 34.6 - type: accuracy name: Bambara Test accuracy value: 12.0 - type: accuracy name: Lithuanian Test accuracy value: 43.5 - type: accuracy name: Galician Test accuracy value: 28.7 - type: accuracy name: Vietnamese Test accuracy value: 36.4 - type: accuracy name: Greek Test accuracy value: 32.5 - type: accuracy name: Catalan Test accuracy value: 25.7 - type: accuracy name: Czech Test accuracy value: 36.8 - type: accuracy name: Erzya Test accuracy value: 20.0 - type: accuracy name: Bhojpuri Test accuracy value: 27.3 - type: accuracy name: Thai Test accuracy value: 32.4 - type: accuracy name: Marathi Test accuracy value: 37.4 - type: accuracy name: Basque Test accuracy value: 38.3 - type: accuracy name: Slovak Test accuracy value: 37.2 - type: accuracy name: Kiche Test accuracy value: 17.2 - type: accuracy name: Yoruba Test accuracy value: 13.2 - type: accuracy name: Warlpiri Test accuracy value: 21.5 - type: accuracy name: Tamil Test accuracy value: 42.5 - type: accuracy name: Maltese Test accuracy value: 17.5 - type: accuracy name: Ancient Greek Test accuracy value: 37.4 - type: accuracy name: Icelandic Test accuracy value: 32.7 - type: accuracy name: Mbya Guarani Test accuracy value: 13.9 - type: accuracy name: Urdu Test accuracy value: 28.1 - type: accuracy name: Romanian Test accuracy value: 34.8 - type: accuracy name: Persian Test accuracy value: 36.2 - type: accuracy name: Apurina Test accuracy value: 21.9 - type: accuracy name: Japanese Test accuracy value: 26.3 - type: accuracy name: Hungarian Test accuracy value: 34.6 - type: accuracy name: Hindi Test accuracy value: 29.3 - type: accuracy name: Classical Chinese Test accuracy value: 30.0 - type: accuracy name: Komi Permyak Test accuracy value: 26.1 - type: accuracy name: Faroese Test accuracy value: 24.8 - type: accuracy name: Sanskrit Test accuracy value: 84.2 - type: accuracy name: Livvi Test accuracy value: 29.7 - type: accuracy name: Arabic Test accuracy value: 32.6 - type: accuracy name: Wolof Test accuracy value: 16.7 - type: accuracy name: Bulgarian Test accuracy value: 35.4 - type: accuracy name: Akuntsu Test accuracy value: 23.9 - type: accuracy name: Makurap Test accuracy value: 14.4 - type: accuracy name: Kangri Test accuracy value: 27.8 - type: accuracy name: Breton Test accuracy value: 27.6 - type: accuracy name: Telugu Test accuracy value: 50.6 - type: accuracy name: Cantonese Test accuracy value: 31.6 - type: accuracy name: Old Church Slavonic Test accuracy value: 43.2 - type: accuracy name: Karelian Test accuracy value: 34.1 - type: accuracy name: Upper Sorbian Test accuracy value: 28.5 - type: accuracy name: South Levantine Arabic Test accuracy value: 30.8 - type: accuracy name: Komi Zyrian Test accuracy value: 25.5 - type: accuracy name: Irish Test accuracy value: 20.8 - type: accuracy name: Nayini Test accuracy value: 29.5 - type: accuracy name: Munduruku Test accuracy value: 15.6 - type: accuracy name: Manx Test accuracy value: 15.9 - type: accuracy name: Skolt Sami Test accuracy value: 18.9 - type: accuracy name: Afrikaans Test accuracy value: 34.5 - type: accuracy name: Old Turkish Test accuracy value: 6.3 - type: accuracy name: Tupinamba Test accuracy value: 25.2 - type: accuracy name: Belarusian Test accuracy value: 39.3 - type: accuracy name: Serbian Test accuracy value: 33.7 - type: accuracy name: Moksha Test accuracy value: 21.8 - type: accuracy name: Western Armenian Test accuracy value: 38.3 - type: accuracy name: Scottish Gaelic Test accuracy value: 23.3 - type: accuracy name: Khunsari Test accuracy value: 29.7 - type: accuracy name: Hebrew Test accuracy value: 39.6 - type: accuracy name: Uyghur Test accuracy value: 50.1 - type: accuracy name: Chukchi Test accuracy value: 14.8 --- # XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Sanskrit 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-sa") model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-sa") ```