Re: [Moses-support] Generating Segment Level BLEU, NIST and METEOR scores

Hi Liling, Asiya generates the segment scores for any metric it has as part of the analysis: http://nlp.lsi.upc.edu/asiya/ Best, Cristina 2015-09-02 21:47 GMT+02:00 liling tan : > Dear Moses devs/users, > > Is there any script in moses or other MT libraries that can

Re: [Moses-support] Generating Segment Level BLEU, NIST and METEOR scores

Hi Liling, All, mt-eval allows for sentence-level calculation of BLEU, NIST, RIBES, and WER: https://github.com/odashi/mteval It doesn't handle METEOR (which is likely too complicated to be properly implemented independently of the main branch), but for the others it's a pretty convenient

[Moses-support] Generating Segment Level BLEU, NIST and METEOR scores

Dear Moses devs/users, Is there any script in moses or other MT libraries that can generate the segment level BLEU, NIST and METEOR scores for each sentence in the test set? Best Regards, Liling ___ Moses-support mailing list Moses-support@mit.edu

Re: [Moses-support] Generating Segment Level BLEU, NIST and METEOR scores

Hi Liling, This tool calculates sentence-level BLEU scores (smoothed via incrementing the n-gram counts by 1): bin/sentence-bleu Make sure that you provide the hypothesis and reference files in an appropriately processed way. The tool doesn't apply any tokenization or remove any markup