Open Maggione opened 6 years ago
Hi, thank you for sharing your codes. I have the same problem, and I really need to know how can I handle this issue. any suggestion...?
meet the same question too~ it is ambiguous in the paper when the author describing the valid&test sets for IWSTL ende 2016
meet the same queation too... I use this preprocessed dataset iwslt.tar.gz /train/train.tags.en-de.bpe.dev.en , and it works
meet the same queation too... can you realease the data example ?
Thank you for sharing your codes. I have a question about how to preprocess the data. For example, for the iwslt en-de dataset, you use a file named train.tags.en-de.bpe.dev.en2 in the script run_alignment_iwslt.sh. It seems to not belong to the original dataset. Where does it come from?