mirror of
https://github.com/Helsinki-NLP/OPUS-MT-train.git
synced 2024-12-02 20:48:08 +03:00
| .. | ||
| README.md | ||
Tatoeba-2020-01-17.zip
- dataset: Tatoeba
- model: transformer-align
- pre-processing: normalization + SentencePiece
- download: Tatoeba-2020-01-17.zip
- test set translations: Tatoeba-2020-01-17.test.txt
- test set scores: Tatoeba-2020-01-17.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| JW300.en.niu | 53.0 | 0.698 |
opus-2020-01-20.zip
- dataset: opus
- model: transformer-align
- pre-processing: normalization + SentencePiece
- download: opus-2020-01-20.zip
- test set translations: opus-2020-01-20.test.txt
- test set scores: opus-2020-01-20.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| JW300.en.niu | 53.0 | 0.698 |
opus+bt-2020-05-23.zip
- dataset: opus+bt
- model: transformer-align
- source language(s): en
- target language(s): niu
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm4k,spm4k)
- download: opus+bt-2020-05-23.zip
- test set translations: opus+bt-2020-05-23.test.txt
- test set scores: opus+bt-2020-05-23.eval.txt
Training data: opus+bt
- en-niu: Tatoeba (23)
- en-niu: total size = 23
- unused dev/test data is added to training data
- total size (opus+bt): 219436
Validation data
-
en-niu: JW300
-
devset = top 2500 lines of JW300.src.shuffled!
-
testset = next 2500 lines of JW300.src.shuffled!
-
remaining lines are added to traindata
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| JW300.en.niu | 52.4 | 0.695 |