opus-2020-07-27.yml

release: phi-eng/opus-2020-07-27.zip
release-date: 2020-07-27
dataset-name: opus
modeltype: transformer
pre-processing: normalization + SentencePiece (spm12k,spm12k)
subwords:
   - source: spm12k
   - target: spm12k
subword-models:
   - source: source.spm
   - target: target.spm
source-languages:
   - akl
   - ceb
   - hil
   - ilo
   - pag
   - war
target-languages:
   - eng
test-data:
   - Tatoeba-test.akl-eng: 27/60
   - Tatoeba-test.ceb-eng: 378/1873
   - Tatoeba-test.hil-eng: 22/127
   - Tatoeba-test.ilo-eng: 1093/6184
   - Tatoeba-test.multi-eng: 405/1933
   - Tatoeba-test.pag-eng: 49/264
   - Tatoeba-test.pmn-eng: 1497/8479
   - Tatoeba-test.war-eng: 1512/9630
BLEU-scores:
   - Tatoeba-test.akl-eng: 5.6
   - Tatoeba-test.ceb-eng: 21.4
   - Tatoeba-test.hil-eng: 9.3
   - Tatoeba-test.ilo-eng: 1.6
   - Tatoeba-test.multi-eng: 21.0
   - Tatoeba-test.pag-eng: 1.9
   - Tatoeba-test.pmn-eng: 0.6
   - Tatoeba-test.war-eng: 3.9
chr-F-scores:
   - Tatoeba-test.akl-eng: 0.208
   - Tatoeba-test.ceb-eng: 0.391
   - Tatoeba-test.hil-eng: 0.280
   - Tatoeba-test.ilo-eng: 0.164
   - Tatoeba-test.multi-eng: 0.385
   - Tatoeba-test.pag-eng: 0.182
   - Tatoeba-test.pmn-eng: 0.102
   - Tatoeba-test.war-eng: 0.209