Thanks again for the explanation!
On Thu, Oct 13, 2016 at 5:22 AM, Philipp Koehn <p...@jhu.edu> wrote:
> check out the dev/test files from WMT:
> The main difference between mteval-13a.pl and multi-bleu.pl is that the
> latter accepts your tokenization of translation and reference, while
> mteval-13a.pl expects detokenized text and performs its own tokenization
> On Tue, Oct 11, 2016 at 8:43 PM, Nat Gillin <nat.gil...@gmail.com> wrote:
>> Dear Moses community,
>> Is it right that the mteval-13a.pl is the canonical BLEU/NIST evaluation
>> used in WMT and by most researches reporting on BLEU?
>> Are there links to sample SGML and XML files that is used by
>> mteval-13a.pl ?
>> I understand that there's also Moses BLEU in the C++ code and also the
>> multi-bleu.pl. Are there other bleu versions out there? Are they the
>> Thanks in advance for the tips!
>> Moses-support mailing list
Moses-support mailing list