Re: [Moses-support] Sparse features

I suppose you're read the page http://www.statmt.org/moses/?n=Moses.SparseFeatures I small, fairly clear feature function that uses sparse feature is TargetBigramFeature The main thing to note 1. It has not dense feature, from the 0 in the constructor TargetBigramFeature::Ta

Re: [Moses-support] EMS MML IndexError: list index out of range

Hi Barry, All the scores are 9 in that file. Thanks, Jian On Fri, Jan 24, 2014 at 3:51 PM, Barry Haddow wrote: > Hi Jian > > This is a bit suspect: > > > 2014-01-24 14:17:26,276 Retaining at least 0 entries and ignoring 2075137 > > Are the scores in this file sensible (or are they all th

[Moses-support] HyTra deadline extension to Feb. 7 (EACL Workshop on Hybrid Approaches to Translation)

*** DEADLINE EXTENSION TO FEBRUARY 7, 2014 *** = THIRD WORKSHOP ON HYBRID APPROACHES TO TRANSLATION (HyTra 2014) Co-located with EACL 2014 http://eacl2014.org/ Gothenburg, Sweden April 27, 2014 http://www.upf.edu/glicom/hytra20

Re: [Moses-support] EMS MML IndexError: list index out of range

Hi Jian This is a bit suspect: 2014-01-24 14:17:26,276 Retaining at least 0 entries and ignoring 2075137 Are the scores in this file sensible (or are they all the same?) /home/mml/mml-test/experiment/training/corpus-mml-score.1 cheers - Barry On 24/01/14 14:53, jian zhang wrote: > Hi, > > I g

Re: [Moses-support] filter parallel corpus

Hi, Moses has an implementation of modified Moore-Lewis filtering which may be roughly what you want: http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc66 -phi On Thu, Jan 16, 2014 at 10:43 AM, Saeed Farzi wrote: > Dear all, > > I am working on a translation task with a very large paral

[Moses-support] EMS MML IndexError: list index out of range

Hi, I got error of IndexError: list index out of range at the TRAINING_mml-filter-before-wa step. I had read the post at https://www.mail-archive.com/moses-support@mit.edu/msg08767.html, however I still can not figure out what is wrong. The full error is general:strategy = Score general:source_

Re: [Moses-support] word alignment-words' indexes and sentences' length

Thank you Barry for your help. Hi Amin, I can't see the link. could you please attach it to your email? Regrads Amir ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support

[Moses-support] Short-term contract in SMT in WIPO

Title: Short-term contract(s) in the field of Statistical Machine Translation (2 months full time or 12 months part-time) Wipo is looking for candidates who could work for a short period of time on specific tasks related to SMT. We are looking for one (or more) skilled computer scientist(s)

Re: [Moses-support] word alignment-words' indexes and sentences' length

Dear Amir, I recently developed a normalizer and tokenizer for Persian language. We used the first version of this tool in our IWSLT submission this year, and got around 1.5 Bleu point improvement over the baseline (which was tokenized using Moses built-in

Re: [Moses-support] word alignment-words' indexes and sentences' length

Hi Amir You can use this tokeniser as a basis for creating your own tokeniser, or you can swap in your own tokeniser. For EMS a tokeniser should read from stdin and write to stdout, so you can run it like this tokeniser [options] < input > output cheers - Barry On 24/01/14 08:58, amir haghigh

Re: [Moses-support] word alignment-words' indexes and sentences' length

I use the built-in tokenizer in the Moses. how can I change this tokenizer? should I change the source code? Regards Amir ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support