afro-xlmr-large / README.md
Davlan's picture
Update README.md
cfff531
|
raw
history blame
1.61 kB
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: afro-xlmr-large
    results: []

afro-xlmr-base

AfroXLMR-large was created by MLM adaptation of XLM-R-large model on 17 African languages (Afrikaans, Amharic, Hausa, Igbo, Malagasy, Chichewa, Oromo, Naija, Kinyarwanda, Kirundi, Shona, Somali, Sesotho, Swahili, isiXhosa, Yoruba, and isiZulu) covering the major African language families and 3 high resource languages (Arabic, French, and English).

Eval results on MasakhaNER (F-score)

language XLM-R-miniLM XLM-R-base XLM-R-large afro-xlmr-large afro-xlmr-base afro-xlmr-small afro-xlmr-mini
amh 69.5 70.6 76.2 -- 76.1 70.1 69.7
hau 74.5 89.5 90.5 -- 91.2 91.4 87.7
ibo 81.9 84.8 84.1 -- 87.4 86.6 83.5
kin 68.6 73.3 73.8 -- 78.0 77.5 74.1
lug 64.7 79.7 81.6 -- 82.9 83.2 77.4
luo 11.7 74.9 73.6 -- 75.1 75.4 17.5
pcm 83.2 87.3 89.0 -- 89.6 89.0 85.5
swa 86.3 87.4 89.4 -- 88.6 88.7 86.0
wol 51.7 63.9 67.9 -- 67.4 65.9 59.0
yor 72.0 78.3 78.9 85.0 82.1 81.3 75.1

BibTeX entry and citation info

@misc{afro_maft,
  doi = {10.48550/ARXIV.2204.06487},
  url = {https://arxiv.org/abs/2204.06487},
  author = {Alabi, Jesujoba O. and Adelani, David Ifeoluwa and Mosbach, Marius and Klakow, Dietrich},
  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}