mirror of
https://github.com/Helsinki-NLP/OPUS-MT-train.git
synced 2024-10-26 21:19:02 +03:00
.. | ||
README.md |
opus-2019-12-05.zip
- dataset: opus
- model: transformer
- pre-processing: normalization + tokenization + BPE
- download: opus-2019-12-05.zip
- test set translations: opus-2019-12-05.test.txt
- test set scores: opus-2019-12-05.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
newstest2012.ru.en | 32.1 | 0.573 |
newstest2013.ru.en | 25.7 | 0.516 |
newstest2014-ruen.ru.en | 29.0 | 0.557 |
newstest2015-enru.ru.en | 27.1 | 0.537 |
newstest2016-enru.ru.en | 26.3 | 0.534 |
newstest2017-enru.ru.en | 29.2 | 0.559 |
newstest2018-enru.ru.en | 26.3 | 0.533 |
newstest2019-ruen.ru.en | 29.5 | 0.548 |
Tatoeba.ru.en | 39.5 | 0.613 |
opus-2019-12-18.zip
- dataset: opus
- model: transformer-align
- pre-processing: normalization + SentencePiece
- download: opus-2019-12-18.zip
- test set translations: opus-2019-12-18.test.txt
- test set scores: opus-2019-12-18.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
newstest2012.ru.en | 27.4 | 0.543 |
newstest2013.ru.en | 24.2 | 0.511 |
newstest2014-ruen.ru.en | 27.4 | 0.556 |
newstest2015-enru.ru.en | 23.2 | 0.506 |
newstest2016-enru.ru.en | 24.8 | 0.526 |
newstest2017-enru.ru.en | 25.4 | 0.524 |
newstest2018-enru.ru.en | 24.5 | 0.522 |
newstest2019-ruen.ru.en | 24.4 | 0.514 |
Tatoeba.ru.en | 56.0 | 0.696 |
opus-2020-01-16.zip
- dataset: opus
- model: transformer-align
- pre-processing: normalization + SentencePiece
- download: opus-2020-01-16.zip
- test set translations: opus-2020-01-16.test.txt
- test set scores: opus-2020-01-16.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
newstest2012.ru.en | 35.3 | 0.606 |
newstest2013.ru.en | 28.2 | 0.547 |
newstest2014-ruen.ru.en | 32.5 | 0.595 |
newstest2015-enru.ru.en | 30.7 | 0.569 |
newstest2016-enru.ru.en | 30.5 | 0.569 |
newstest2017-enru.ru.en | 33.8 | 0.596 |
newstest2018-enru.ru.en | 30.0 | 0.569 |
newstest2019-ruen.ru.en | 32.0 | 0.581 |
Tatoeba.ru.en | 59.8 | 0.726 |
opus-2020-02-11.zip
- dataset: opus
- model: transformer-align
- pre-processing: normalization + SentencePiece
- download: opus-2020-02-11.zip
- test set translations: opus-2020-02-11.test.txt
- test set scores: opus-2020-02-11.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
newstest2012.ru.en | 34.8 | 0.603 |
newstest2013.ru.en | 28.1 | 0.546 |
newstest2014-ruen.ru.en | 32.1 | 0.593 |
newstest2015-enru.ru.en | 30.3 | 0.567 |
newstest2016-enru.ru.en | 30.1 | 0.566 |
newstest2017-enru.ru.en | 33.4 | 0.593 |
newstest2018-enru.ru.en | 29.6 | 0.566 |
newstest2019-ruen.ru.en | 31.5 | 0.577 |
Tatoeba.ru.en | 60.8 | 0.734 |
opus-2020-02-26.zip
- dataset: opus
- model: transformer-align
- pre-processing: normalization + SentencePiece
- download: opus-2020-02-26.zip
- test set translations: opus-2020-02-26.test.txt
- test set scores: opus-2020-02-26.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
newstest2012.ru.en | 34.8 | 0.603 |
newstest2013.ru.en | 27.9 | 0.545 |
newstest2014-ruen.ru.en | 31.9 | 0.591 |
newstest2015-enru.ru.en | 30.4 | 0.568 |
newstest2016-enru.ru.en | 30.1 | 0.565 |
newstest2017-enru.ru.en | 33.4 | 0.593 |
newstest2018-enru.ru.en | 29.6 | 0.565 |
newstest2019-ruen.ru.en | 31.4 | 0.576 |
Tatoeba.ru.en | 61.1 | 0.736 |