Hi Saeed,

I fully agree with you. I don't think that in Physics, for example, a 
paper without a reliable estimation of the error on the measurements 
would be publishable, nor would you see in a paper results with more 
digits than the significant ones.
Having easy-to-use statistical significant tests in the Moses pipeline 
seems a great idea to spread good practices in the community. Maybe a 
good project idea for next MT Marathon (or is it already available in 
Moses)?

Patrik

> Just a suggestion: IMHO, adding a significance test implementation to 
> Moses
> will help users to report such tests. I do not get good feelings when I
> read a paper with no statistical significance tests. 
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to