<div style="font-family: Helvetica; min-height:52px;
-webkit-tap-highlight-color: rgba(0, 0, 0, 0);">Ok obviously this is a modified
bleu algorithm, similar to what sentence-bleu does.<div>However I believe this
is still not right for unigram
sentences.<br><br><br><br>____________________<br><br>De : "Vincent Nguyen"
<vngu...@neuf.fr><br>Date : 26 févr. 2016 22:21:59<br>A :
moses-support@mit.edu<br><br>Sujet : Re: [Moses-support] bleu-annotation /
analysis.perl<br><br><br>Am I correct saying that when sentences length is less
or equal to 4 <br>tokens then the BLEU score should be 1 for exact matches and
0 when not <br>exact match ?<br>(by definition of
http://www1.cs.columbia.edu/nlp/sgd/bleu.pdf)<br><br><br>Le <a dir="ltr"
href="tel:26/02/2016" x-apple-data-detectors="true"
x-apple-data-detectors-type="telephone"
x-apple-data-detectors-result="2">26/02/2016</a> 10:02, Vincent Nguyen a écrit
:<br>
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support