metadata

pipeline_tag: translation
language:
  - multilingual
  - af
  - am
  - ar
  - as
  - az
  - be
  - bg
  - bn
  - br
  - bs
  - ca
  - cs
  - cy
  - da
  - de
  - el
  - en
  - eo
  - es
  - et
  - eu
  - fa
  - fi
  - fr
  - fy
  - ga
  - gd
  - gl
  - gu
  - ha
  - he
  - hi
  - hr
  - hu
  - hy
  - id
  - is
  - it
  - ja
  - jv
  - ka
  - kk
  - km
  - kn
  - ko
  - ku
  - ky
  - la
  - lo
  - lt
  - lv
  - mg
  - mk
  - ml
  - mn
  - mr
  - ms
  - my
  - ne
  - nl
  - 'no'
  - om
  - or
  - pa
  - pl
  - ps
  - pt
  - ro
  - ru
  - sa
  - sd
  - si
  - sk
  - sl
  - so
  - sq
  - sr
  - su
  - sv
  - sw
  - ta
  - te
  - th
  - tl
  - tr
  - ug
  - uk
  - ur
  - uz
  - vi
  - xh
  - yi
  - zh
license: cc-by-nc-sa-4.0

This is a COMET evaluation model: It receives a triplet with (source sentence, translation, reference translation) and returns a score that reflects the quality of the translation compared to both source and reference.

This model was developed using UniTE architecture but using the same data and hyperparameters from Unbabel/wmt22-comet-da.

We build this model for our paper: The Inside Story (Rei et al., ACL 2023)

Paper

The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics (Rei et al., ACL 2023)
UniTE: Unified Translation Evaluation (Wan et al., ACL 2022)
COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task (Rei et al., WMT 2022)

License

cc-by-nc-sa-4.0

Usage (unbabel-comet)

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 -r {references}.txt --model Unbabel/wmt22-comet-da

Or using Python:

from comet import download_model, load_from_checkpoint

model_path = download_model("Unbabel/wmt22-unite-da")
model = load_from_checkpoint(model_path)
data = [
    {
        "src": "Dem Feuer konnte Einhalt geboten werden",
        "mt": "The fire could be stopped",
        "ref": "They were able to control the fire."
    },
    {
        "src": "Schulen und Kindergärten wurden eröffnet.",
        "mt": "Schools and kindergartens were open",
        "ref": "Schools and kindergartens opened"
    }
]
model_output = model.predict(data, batch_size=8, gpus=1)
print (model_output)

Intended uses

Our model is intented to be used for MT evaluation.

Given a a triplet with (source sentence, translation, reference translation) outputs three scores that reflect the translation quality according to different inputs: - source score: [`mt`, `src`] - reference score: [`mt`, `ref`] - unified score: [`mt`, `src`, `ref`]

Languages Covered:

This model builds on top of XLM-R which cover the following languages:

Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bengali, Bengali Romanized, Bosnian, Breton, Bulgarian, Burmese, Burmese, Catalan, Chinese (Simplified), Chinese (Traditional), Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hindi Romanized, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish (Kurmanji), Kyrgyz, Lao, Latin, Latvian, Lithuanian, Macedonian, Malagasy, Malay, Malayalam, Marathi, Mongolian, Nepali, Norwegian, Oriya, Oromo, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskri, Scottish, Gaelic, Serbian, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tamil, Tamil Romanized, Telugu, Telugu Romanized, Thai, Turkish, Ukrainian, Urdu, Urdu Romanized, Uyghur, Uzbek, Vietnamese, Welsh, Western, Frisian, Xhosa, Yiddish.

Thus, results for language pairs containing uncovered languages are unreliable!