đ XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Naija
This model is designed for part - of - speech tagging in Naija and other languages, leveraging cross - lingual transfer technology.
đ Quick Start
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.
đģ Usage Examples
Basic Usage
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")
đ Documentation
| Property |
Details |
| Language |
pcm |
| License |
apache - 2.0 |
| Library Name |
transformers |
| Tags |
part - of - speech, token - classification |
| Datasets |
universal_dependencies |
| Metrics |
accuracy |
Model Results
The model named xlm-roberta-base-ft-udpos28-pcm has the following results in the token - classification task (Part - of - Speech Tagging) on the Universal Dependencies v2.8 dataset:
| Language |
Test Accuracy |
| English |
77.2 |
| Dutch |
75.2 |
| German |
73.2 |
| Italian |
68.9 |
| French |
74.0 |
| Spanish |
75.1 |
| Russian |
70.3 |
| Swedish |
78.9 |
| Norwegian |
74.3 |
| Danish |
73.4 |
| Low Saxon |
37.9 |
| Akkadian |
28.0 |
| Armenian |
65.4 |
| Welsh |
59.7 |
| Old East Slavic |
61.0 |
| Albanian |
66.1 |
| Slovenian |
67.6 |
| Guajajara |
16.1 |
| Kurmanji |
54.8 |
| Turkish |
58.2 |
| Finnish |
67.4 |
| Indonesian |
68.5 |
| Ukrainian |
68.1 |
| Polish |
68.8 |
| Portuguese |
72.9 |
| Kazakh |
60.1 |
| Latin |
64.3 |
| Old French |
51.1 |
| Buryat |
38.9 |
| Kaapor |
16.7 |
| Korean |
52.4 |
| Estonian |
68.3 |
| Croatian |
73.0 |
| Gothic |
21.4 |
| Swiss German |
33.4 |
| Assyrian |
0.0 |
| North Sami |
24.3 |
| Naija |
97.9 |
| Latvian |
66.3 |
| Chinese |
34.3 |
| Tagalog |
49.9 |
| Bambara |
16.7 |
| Lithuanian |
65.7 |
| Galician |
72.4 |
| Vietnamese |
54.3 |
| Greek |
73.3 |
| Catalan |
73.6 |
| Czech |
69.5 |
| Erzya |
22.1 |
| Bhojpuri |
36.6 |
| Thai |
65.4 |
| Marathi |
50.3 |
| Basque |
58.5 |
| Slovak |
70.4 |
| Kiche |
8.0 |
| Yoruba |
6.1 |
| Warlpiri |
15.4 |
| Tamil |
60.1 |
| Maltese |
12.2 |
| Ancient Greek |
45.8 |
| Icelandic |
72.5 |
| Mbya Guarani |
11.4 |
| Urdu |
59.1 |
| Romanian |
64.8 |
| Persian |
67.2 |
| Apurina |
15.5 |
| Japanese |
26.1 |
| Hungarian |
68.6 |
| Hindi |
65.0 |
| Classical Chinese |
30.4 |
| Komi Permyak |
21.2 |
| Faroese |
61.6 |
| Sanskrit |
25.6 |
| Livvi |
39.7 |
| Arabic |
63.5 |
| Wolof |
15.9 |
| Bulgarian |
74.6 |
| Akuntsu |
26.5 |
| Makurap |
11.6 |
| Kangri |
27.8 |
| Breton |
46.6 |
| Telugu |
59.4 |
| Cantonese |
30.7 |
| Old Church Slavonic |
36.7 |
| Karelian |
45.9 |
| Upper Sorbian |
49.3 |
| South Levantine Arabic |
42.5 |
| Komi Zyrian |
18.4 |
| Irish |
48.3 |
| Nayini |
24.4 |
| Munduruku |
16.1 |
| Manx |
14.7 |
| Skolt Sami |
5.4 |
| Afrikaans |
76.5 |
| Old Turkish |
0.0 |
| Tupinamba |
16.3 |
| Belarusian |
70.7 |
| Serbian |
74.8 |
| Moksha |
24.1 |
| Western Armenian |
59.8 |
| Scottish Gaelic |
45.4 |
| Khunsari |
21.6 |
| Hebrew |
65.6 |
| Uyghur |
55.0 |
| Chukchi |
12.6 |
đ License
The model is released under the apache - 2.0 license.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
PyTorch