Re: [Moses-support] How to score sentences using SRILM

ophe.ser...@gmail.com> wrote: > Hi Tharaka, > You may use the perplexity with the switch -ppl with the > tool "ngram" and if you want some details you can add the switch -debug > <1,2...> to have more details. > > Cheers, > > Christophe > > > L

[Moses-support] How to score sentences using SRILM

Hi All, I need use SRILM to score different sentences .Is there any scripts available for this or do i need to write my own script ? Can anybody guide me how to do this.. Thanks in advance, Tharaka ___ Moses-support mailing list Moses-support@mit.edu h

Re: [Moses-support] Moses-support Digest, Vol 69, Issue 66

Hi everybody, I'm new to moses and i'm doing a english- sinhala (Language used in sri lanka) translation.. But when i used the provided tokenizer to tokenize sinhala datafile i found that it's tokenizing in a wrong way. so i created a nonbreaking_prefix file for sinhala.. But it's not working. I

Re: [Moses-support] tokenizer problem

les in > this > > folder all have the same name with a 2-letter language code extension. > These > > file have language-specific rules for how the tokenizer & detokenizer > work. > > > > Anyone, is there a better resource than reading the existing files to > learn > >

Re: [Moses-support] tokenizer problem

r & detokenizer > work. > > Anyone, is there a better resource than reading the existing files to > learn how the files work? > > Tom > > > > On Wed, 30 May 2012 18:22:52 +0530, tharaka weheragoda < > tharakadum...@gmail.com> wrote: > > Thank you very

Re: [Moses-support] tokenizer problem

; > > On Wed, 30 May 2012 17:37:19 +0530, tharaka weheragoda < > tharakadum...@gmail.com> wrote: > > Hi everybody, > > When i'm trying to tokenize my sinhala dataset it gives me a warning > message like this > "WARNING: No known abbreviations for language &#

[Moses-support] tokenizer problem

Hi everybody, When i'm trying to tokenize my sinhala dataset it gives me a warning message like this "WARNING: No known abbreviations for language 'si', attempting fall-back to English version..." And my letters have changed a bit. Is their anyway to tokenize sinhala data with this tokenizer.p

[Moses-support] tuning set

Hi, i'm new to this field and i'm confused about the use of tuning set? Actually waht's the purpose of using a tuning set here? Thanks in advance ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support

[Moses-support] minimum amount of parallel data required for SMT to perform well

Hi All, If anybody knows about the minimum amount of parallel data required for SMT to perform well please let me know. Thanks in advance! Tharaka ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-suppor

[Moses-support] giza ++ error

Hi, When i train the phrase table i get these errors and terminate execution. nohup: ignoring input Using SCRIPTS_ROOTDIR: /home/tharaka/Desktop/project/tools/moses/scripts Using single-thread GIZA (1) preparing corpus @ Sun Apr 22 00:41:50 IST 2012 Executing: mkdir -p work/corpus (1.0) selecting

[Moses-support] giza ++ error

Hi, I tried to train phrase table with giza ++. I got these errors in the training.out file. nohup: ignoring input Using SCRIPTS_ROOTDIR: /home/tharaka/Desktop/project/tools/moses/scripts Using single-thread GIZA (1) preparing corpus @ Sat Apr 21 20:34:43 IST 2012 Executing: mkdir -p work/corpus (