dear all, i've been using the moses baseline site and the commands seem to do just fine but i just couldn't pass the following step: export IRSTLM=/home/eleni/irstlm; ~/irstlm/bin/build-lm.sh -inews-commentary-v7.fr-en.sb.en -t ./tmp -p -s improved-kneser-ney -o news-commentary-v7.fr-en.lm.en when i try to run the above command, it displays the following: Temporary directory ./tmp not found
creating ./tmp Extracting dictionary from training corpus Splitting dictionary into 3 lists Extracting n-gram statistics for each word list Important: dictionary must be ordered according to order of appearance of words in data used to generate n-gram blocks, so that sub language model blocks results ordered too dict.* Estimating language models for each word list ls: cannot access ./tmp/dict.*: No such file or directory (is there supposed to be a dict.* in the tmp directory?) Merging language models into news-commentary-v7.fr-en.lm.en Cleaning temporary directory ./tmp Removing temporary directory ./tmp then i ignored the above and tried to run the next command: ~/irstlm/bin/compile-lm --text yes news-commentary-v7.fr-en.lm.en.gz news-commentary-v7.fr-en.arpa.en then it displayed the following: inpfile: news-commentary-v7.fr-en.lm.en.gz loading up to the LM level 1000 (if any) dub: 10000000 Failed to open news-commentary-v7.fr-en.lm.en.gz! is there any solution as to what the problem could be? than you in advance for all your help. regards, Eleni
_______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
