Re: [Moses-support] Performance issues using Moses Server with Moses 3
Hi Oren The threading model is different. In v1, the server created a new thread for every request, v3 uses a thread pool. Try increasing the number of threads. Also, make sure you use the compact phrase table and KenLM as they are normally faster, and pre-pruning your phrase table can help, cheers - Barry On 20/07/15 12:01, Oren wrote: Hi all, We are in the process of migrating from Moses 1 to Moses 3. We have noticed a significant slowdown when sending many requests at once to Moses Server. The first request will actually finish about 25% faster that a single request using Moses 1, but as more requests accumulate there is a marked slowdown, until requests take 5 times longer or more. Is this a known issue? Is it specific to Moses Server? What can we do about it? Thanks! Oren. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
[Moses-support] Performance issues using Moses Server with Moses 3
Hi all, We are in the process of migrating from Moses 1 to Moses 3. We have noticed a significant slowdown when sending many requests at once to Moses Server. The first request will actually finish about 25% faster that a single request using Moses 1, but as more requests accumulate there is a marked slowdown, until requests take 5 times longer or more. Is this a known issue? Is it specific to Moses Server? What can we do about it? Thanks! Oren. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
[Moses-support] Errors in tuning Moses
Hello, I am trying to train the 'moses.ini' file with 'mert-moses.pl' script. The exact command I am running is nohup nice $myPATH/mosesdecoder/scripts/training/mert-moses.pl --decoder-flags=threads 4 \ $myPATH/working/tuningcorpus/prepared-corpus/news-test2008.clean.fr $myPATH/working/tuningcorpus/prepared-corpus/news-test2008.clean.en \ $myPATH/working/train/model/moses.ini --mertdir $myPATH/working/train/model mert.out However I am getting the following error in 'mert.out' file: Using SCRIPTS_ROOTDIR: /media/sudip/linuxdata1/mosesdecoder/scripts Not executable: /media/sudip/linuxdata1/working/train/model/extractor at /media/sudip/linuxdata1/mosesdecoder/scripts/training/mert-moses.pl line 362. I don't quite understand this error, please help. Thanks in advance - Regards, Sudip C. Mahajan | Ph.D. Student,Dept. of Technology University of Pune ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] Getting started - Best practices
On 19/07/2015 23:06, Vincent Nguyen wrote: I finally went through the all Baseline process with the KenLM model. results are mitigated, so from here what would be the best practices ? 1) I saw online a bunch of corpus available from the European Union should this be used to train the translation system AND the langue model or just one of the 2 ? you cab use the data for creating both the language model and the translation model. The only thing you have to make sure is that your training data is not part of the tuning or test data 2) Is there a benchmark between the different model (Kenlm, Irstlm, ...) ie is there a big difference in the observed results ? is it worth trying several ones ? Try it yourself and tell us the results. 3) I read an article mentioning that the results after the tuning were not as good as before ... does this make any sense ? If you report BLEU score without tuning first, you will be crucified, see this thread: https://www.mail-archive.com/moses-support@mit.edu/msg12593.html You MUST tune. Tuning can sometime to difficult. See this post on how to pick a good tuning set: https://www.mail-archive.com/moses-support@mit.edu/msg12594.html Thanks. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- Hieu Hoang Researcher New York University, Abu Dhabi http://www.hoang.co.uk/hieu ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
