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: apache-2.0

This model was developed by the NLP2CT Lab at the University of Macau and Alibaba Group, and all credits should be attributed to these groups. Since it was developed using the COMET codebase, we adapted the code to run these models within COMET."

This is equivalent to [UniTE-MUP-large] from modelscope

Paper

UniTE: Unified Translation Evaluation (Wan et al., ACL 2022)

Original Code

UniTE

License

Apache 2.0

Usage (unbabel-comet)

Using this model requires unbabel-comet (>=2.0.0) to be installed:

pip install --upgrade pip  # ensures that pip is current 
pip install "unbabel-comet>=2.0.0"

Then you can use it through comet CLI:

comet-score -s {source-inputs}.txt -t {translation-outputs}.txt -r {references}.txt --model Unbabel/unite-mup

Or using Python:

from comet import download_model, load_from_checkpoint

model_path = download_model("Unbabel/unite-mup")
model = load_from_checkpoint(model_path)
data = [
    {
        "src": "这是个句子。",
        "mt": "This is a sentence.",
        "ref": "It is a sentence."
    },
    {
        "src": "这是另一个句子。",
        "mt": "This is another sentence.",
        "ref": "It is another sentence."
    }
]
model_output = model.predict(data, batch_size=8, gpus=1)

# Expected SRC score:
# [0.3474583327770233, 0.4492775797843933]
print (model_output.metadata.src_scores)

# Expected REF score:
# [0.9252626895904541, 0.899452269077301]
print (model_output.metadata.ref_scores)

# Expected UNIFIED score:
# [0.8758717179298401, 0.8294666409492493]
print (model_output.metadata.unified_scores)

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!