Journal: Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing
Languages: Afrikaans, Akkadian, Amharic, Ancient Greek, Arabic, Armenian, Bambara, Basque, Belarussian, Breton, Bulgarian, Buryat, Cantonese, Catalan, Chinese, Coptic, Croatian, Czech, Danish, Dutch, English, Erzya, Estonian, Faroese, Finnish, French, Galician, German, Gothic, Greek, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Kazakh, Komi Zyrian, Korean, Kurmanji, Latin, Latvian, Lithuanian, Maltese, Marathi, Naija, North Sami, Norwegian, Old Church Slavonic, Old French, Persian, Polish, Portuguese, Romanian, Russian, Sanskrit, Serbian, Slovak, Slovenian, Spanish, Swedish, Tagalog, Tamil, Telugu, Thai, Turkish, Ukrainian, Upper Sorbian, Urdu, Uyghur, Vietnamese, Warlpiri, Yoruba
Programming languages: Python
Project website: https://github.com/hyperparticle/udify
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages.