pipeline_tag: translation
language:
- multilingual
- en
- am
- ar
- so
- sw
- pt
- af
- fr
- zu
- mg
- ha
- sn
- arz
- ny
- ig
- xh
- yo
- st
- rw
- tn
- ti
- ts
- om
- run
- nso
- ee
- ln
- tw
- pcm
- gaa
- loz
- lg
- guw
- bem
- efi
- lue
- lua
- toi
- ve
- tum
- tll
- iso
- kqn
- zne
- umb
- mos
- tiv
- lu
- ff
- kwy
- bci
- rnd
- luo
- wal
- ss
- lun
- wo
- nyk
- kj
- ki
- fon
- bm
- cjk
- din
- dyu
- kab
- kam
- kbp
- kr
- kmb
- kg
- nus
- sg
- taq
- tzm
- nqo
license: apache-2.0
This is an improved version of AfriCOMET-QE-STL (quality estimation single task) evaluation model: It receives a source sentence, and a translation, and returns a score that reflects the quality of the translation compared to the source. Different from the original AfriCOMET-QE-STL, this QE model is based on an improved African enhanced encoder, afro-xlmr-large-76L, which leads better performance on quality estimation of African-related machine translation, verified in WMT 2024 Metrics Shared Task.
Paper
AfriMTE and AfriCOMET: Empowering COMET to Embrace Under-resourced African Languages (Wang et al., arXiv 2023)
License
Apache-2.0
Usage (AfriCOMET)
Using this model requires unbabel-comet to be installed:
pip install --upgrade pip # ensures that pip is current
pip install unbabel-comet
Then you can use it through comet CLI:
comet-score -s {source-inputs}.txt -t {translation-outputs}.txt --model masakhane/africomet-qe-stl
Or using Python:
from comet import download_model, load_from_checkpoint
model_path = download_model("masakhane/africomet-qe-stl")
model = load_from_checkpoint(model_path)
data = [
{
"src": "Nadal sàkọọ́lẹ̀ ìforígbárí o ní àmì méje sóódo pẹ̀lú ilẹ̀ Canada.",
"mt": "Nadal's head to head record against the Canadian is 7–2.",
},
{
"src": "Laipe yi o padanu si Raoniki ni ere Sisi Brisbeni.",
"mt": "He recently lost against Raonic in the Brisbane Open.",
}
]
model_output = model.predict(data, batch_size=8, gpus=1)
print (model_output)
Intended uses
Our model is intented to be used for MT quality estimation.
Given a source sentence and a translation outputs a single score between 0 and 1 where 1 represents a perfect translation.