FSMT Model description This is a ported version of fairseq wmt19 transformer for ru en. For more details, please see, Facebook FAIR's WMT19 News Translation Task Submission. The abbreviation FSMT stands for FairSeqMachineTranslation All four models are available: wmt19 en ru wmt19 ru en wmt19 en de wmt19 de en Intended uses & limitations How to use Limitations and bias The original (and this ported model) doesn't seem to handle well inputs with repeated sub phrases, content gets truncated Training data Pretrained weights were left identical to the original model released by fairseq. For more details, please, see the paper. Eval results pair fairseq transformers ru en 41.3 39.20 The score is slightly below the score reported by fairseq , since transformers currently doesn't support: model ensemble, therefore the best performing checkpoint was ported ( model4.pt ). re ranking The score was calculated using this code: note: fairseq reports using a beam of 50, so you should get a slightly higher score if re run with num beams 50 . Data Sources training, etc. test set BibTeX entry and citation info TODO port model ensemble (fairseq uses 4 model checkpoints)
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy