Hi, OK, thanks for the info! Yes, I realise the performance problems, but I am at this time mostly looking for a comparison of a language model in moses (compared to e.g srilm). Being able to plug it in via a socket could be an easy way to try a few things.
-peter ps: temporary blindness caused me to think my message didn't make it to the list :-) On Nov 17, 2011, at 2:53 PM, Hieu Hoang wrote: > hi peter > > i think christian federmann worked on the remote LM : > > https://www.google.com/search?hl=en&q=federmann+Very+large+language+models+for+machine+translation > however, IMO, the decoder is lacking the infrastructure to do remote LM. > > to do it well, the decoder has to batch the LM calls to minimise second > too many queries. Also, it has to make the calls asynchronously rather > than wait for the LM query to complete. > > I'm not sure how far christian got but i suspect this is a major > undertaking > > ps. your email to the mailing list went through fine. Why did you think > it didn't? > http://news.gmane.org/gmane.comp.nlp.moses.user > > On 17/11/2011 14:54, P.J. Berck wrote: >> Hi, >> >> I was looking at the possibility to use a remote LM in moses, but I can't >> find any documentation. >> >> I know about the "6 0 3 host:port" specification in moses.ini, but a naive >> test just gives errors like "Your data contains<s> in a position other than >> the first word." >> >> Is there some kind of protocol I need to implement? What kind of results >> does moses expect? >> >> Thanks for pointers, >> -peter >> >> >> _______________________________________________ >> Moses-support mailing list >> [email protected] >> http://mailman.mit.edu/mailman/listinfo/moses-support >> >> > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
