Hi all, I’ve been seeing a lot of papers where they they changed the decoder parameters such as the weights of the translation model, language model, distortion model, and the word penalty. Some change the max phrase lengths of the decoder. Where do I exactly change this parameters in order to achieve a better translation ?
Sent from Mail for Windows 10 |
_______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support