Re: [Moses-support] Existing documentation to use own language models

there's a example language model code moses/LM/SkeletonLM.* On 21/09/2015 19:24, Arturo Argueta wrote: I was wondering if there's any documentation out there on how to use/integrate a self-made LM on moses. Any pointers will be appreciated. Thanks

Re: [Moses-support] Regarding an error on estimating language model

you can try using the KENLM estimation tool http://www.statmt.org/moses/?n=FactoredTraining.BuildingLanguageModel#ntoc20 On 21/09/2015 13:38, Shubham Tripathi wrote: I have been following your tutorials on building a language model and I am facing difficulties in it. The web page I am referring

Re: [Moses-support] Error while installing moses

you must have the bzip library installed on your computer. Please see this page to see how you can install it for your operating system http://www.statmt.org/moses/?n=Development.GetStarted Hieu Hoang http://www.hoang.co.uk/hieu On 23 September 2015 at 11:49, surya

Re: [Moses-support] experiment.perl, processPhraseTableMin and threads option

Hi, I ran the command as you provided it, and it worked. The "-threads all" functionality was added in August - did you compile the latest version of the code? -phi On Tue, Sep 22, 2015 at 12:16 PM, Tomasz Gawryl wrote: > Hi, > > I'm trying to add this line to

[Moses-support] Error while installing moses

Hi, I am not able to install moses with boost. Every time, I try, it is giving some error. Below are the list of commands that I have used for installing moses. cd boost_1_55_0/ surya@Surya-desktop:~/MTP/moses/boost_1_55_0$ ./bootstrap.sh surya@Surya-desktop:~/MTP/moses/boost_1_55_0$ ./b2

Re: [Moses-support] Kendall's tau metric

Hi, you can tell mert the scorer type with "--sctype": http://www.statmt.org/moses/?n=FactoredTraining.Tuning The KENDALL scorer is likely doing what you want. You can specify a combination of scorers --sctype KENDALL,BLEU --scconfig weights:0.6+0.4 -phi 2015-09-19 10:11 GMT+02:00 Arefeh

Re: [Moses-support] experiment.perl, processPhraseTableMin and threads option

Hi Philipp, Shame on me, you are right. Thanx for help! Regards, TG From: phko...@gmail.com [mailto:phko...@gmail.com] On Behalf Of Philipp Koehn Sent: Wednesday, September 23, 2015 3:30 PM To: Tomasz Gawryl Cc: moses-support@mit.edu Subject: Re: [Moses-support] experiment.perl,

Re: [Moses-support] Problem in Accuracy

Hi, you can test the language model in isolation. Typically, we try to minimize perplexity, so you can run the language model on a test set and check the perplexity score. Running the language model on a test set also helps you with debugging, since it prints out which n-grams are found in the

Re: [Moses-support] is there a way to remove a bad entry in the phrase table ?

Vincent, If you suspect bad entries, isn't it better to address the root of the problem and prepare your training corpus better? On 9/23/2015 6:46 PM, moses-support-requ...@mit.edu wrote: Date: Tue, 22 Sep 2015 20:24:02 +0200 From: Philipp Koehn Subject: Re: [Moses-support] is

Re: [Moses-support] is there a way to remove a bad entry in the phrase table ?

I agree and would like to. But this is tricky, look at the first 30 lines of my phrase table below. and this happens a lot in the first line of tables where there are or weird codes, EN/FR pairs do not match. ! ! ! ! ||| ! ! ! ! ||| 0.103413 0.132185 0.103413 0.401758 ||| 0-0 1-1 2-2 3-3