Hi Team, Please suggest me the Dataset for production quality translations. I have tried with Europarl-en-fr-(V7) data with Trigram-KenLM model.
But results are not satisfactory. My question is, (a) Which data set i should use for production quality translation or What should be size of dataset ? (b) What should be the n-gram order for production quality translation? (c) What language model you would recommend ? I am following the baseline instructions from Statistical Machine Translation System User Manual and Code Guide <https://www.google.co.in/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwj5p_eA9b3XAhXHv48KHWB1Db4QFggnMAA&url=http%3A%2F%2Fwww.statmt.org%2Fmoses%2Fmanual%2Fmanual.pdf&usg=AOvVaw2DpQgCZ-N5KO_KizZl0eo2> . I am a week old in Moses, hence apologies for naive questions. Thanks & Regards, Alind Billore -- Regards, Alind Billore +91-776-996-0259
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
