Open h-asano opened 5 years ago
The published system is not exactly the same system we trained for the paper as we have lost the original models and config files. I reconstructed the system with a newer version of Marian, and there are several reasons why M2 scores are different:
So these are changes that someone could make while reconstructing our systems from scratch using the same data. The training data, subword segmentation codes, and vocabularies are exactly the same.
Thank you very much !
Your reported M2 score on CoNLL2014 is 57.53. In your paper, the M2 score is 55.8.