opus-2020-07-06.yml

release: eng-sla/opus-2020-07-06.zip
release-date: 2020-07-06
dataset-name: opus
modeltype: transformer
pre-processing: normalization + SentencePiece (spm32k,spm32k)
subwords:
   source: spm32k
   target: spm32k
subword-models:
   source: source.spm
   target: target.spm
source-languages:
   - eng
target-languages:
   - bel
   - bos
   - bul
   - ces
   - csb
   - dsb
   - hrv
   - hsb
   - mkd
   - orv
   - pol
   - rue
   - rus
   - slv
   - srp
   - ukr
use-target-labels:
   - ">>bel<<"
   - ">>bel_Latn<<"
   - ">>bos_Latn<<"
   - ">>bul<<"
   - ">>bul_Latn<<"
   - ">>ces<<"
   - ">>csb_Latn<<"
   - ">>dsb<<"
   - ">>hrv<<"
   - ">>hsb<<"
   - ">>mkd<<"
   - ">>orv_Cyrl<<"
   - ">>pol<<"
   - ">>rue<<"
   - ">>rus<<"
   - ">>slv<<"
   - ">>srp_Cyrl<<"
   - ">>srp_Latn<<"
   - ">>ukr<<"
test-data:
   Tatoeba-test.eng-bel: 2500/12908
   Tatoeba-test.eng-bul: 10000/56740
   Tatoeba-test.eng-ces: 10000/52129
   Tatoeba-test.eng-csb: 27/196
   Tatoeba-test.eng-dsb: 34/140
   Tatoeba-test.eng-hbs: 10000/52571
   Tatoeba-test.eng-hsb: 40/156
   Tatoeba-test.eng-mkd: 10000/51245
   Tatoeba-test.eng-multi: 10000/52089
   Tatoeba-test.eng-orv: 322/1364
   Tatoeba-test.eng-pol: 10000/52166
   Tatoeba-test.eng-rue: 120/369
   Tatoeba-test.eng-rus: 10000/53367
   Tatoeba-test.eng-slv: 2007/9410
   Tatoeba-test.eng-ukr: 10000/47921
BLEU-scores:
   Tatoeba-test.eng-bel: 21.8
   Tatoeba-test.eng-bul: 46.2
   Tatoeba-test.eng-ces: 41.3
   Tatoeba-test.eng-csb: 1.3
   Tatoeba-test.eng-dsb: 2.2
   Tatoeba-test.eng-hbs: 1.0
   Tatoeba-test.eng-hsb: 4.4
   Tatoeba-test.eng-mkd: 43.0
   Tatoeba-test.eng-multi: 39.5
   Tatoeba-test.eng-orv: 0.6
   Tatoeba-test.eng-pol: 40.9
   Tatoeba-test.eng-rue: 0.9
   Tatoeba-test.eng-rus: 39.2
   Tatoeba-test.eng-slv: 17.9
   Tatoeba-test.eng-ukr: 37.3
chr-F-scores:
   Tatoeba-test.eng-bel: 0.476
   Tatoeba-test.eng-bul: 0.646
   Tatoeba-test.eng-ces: 0.614
   Tatoeba-test.eng-csb: 0.195
   Tatoeba-test.eng-dsb: 0.065
   Tatoeba-test.eng-hbs: 0.080
   Tatoeba-test.eng-hsb: 0.237
   Tatoeba-test.eng-mkd: 0.625
   Tatoeba-test.eng-multi: 0.601
   Tatoeba-test.eng-orv: 0.115
   Tatoeba-test.eng-pol: 0.627
   Tatoeba-test.eng-rue: 0.106
   Tatoeba-test.eng-rus: 0.602
   Tatoeba-test.eng-slv: 0.349
   Tatoeba-test.eng-ukr: 0.588