[Moses-support] NULL token
Hello, In the theory we learn that the null token is place in the beginning of each sentence. But in the output file of a real system it is seem there is not such a token implicitly. -- Best Regards, S.Bakhshaei ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] NULL token
Hi, the NULL token is an implicit concept of word alignment (and it not placed at any specific position). You can see it popping up in the the lexical translation tables, but otherwise it is invisible. -phi On Mon, Oct 25, 2010 at 11:45 AM, Somayeh Bakhshaei wrote: > Hello, > > In the theory we learn that the null token is place in the beginning of > each sentence. But in the output file of a real system it is seem there is > not such a token implicitly. > > -- > Best Regards, > S.Bakhshaei > > ___ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support > > ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] bag of words language model
Hi, I am not familiar with that, but somewhat related is Arne Mauser's global lexical model, which also exists as a secret feature in Moses (secret because no effiencient training exists): Citation: A. Mauser, S. Hasan, and H. Ney. Extending Statistical Machine Translation with Discriminative and Trigger-Based Lexicon Models. In Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, August 2009. http://www-i6.informatik.rwth-aachen.de/publications/download/628/MauserArneHasanSav%7Bs%7DaNeyHermann--ExtendingStatisticalMachineTranslationwithDiscriminativeTrigger-BasedLexiconModels--2009.pdf -phi On Fri, Oct 22, 2010 at 7:02 PM, Francis Tyers wrote: > Hello all, > > I have a rather strange request. Does anyone know of any papers (or > impementations) on bag-of-words language models ? That is, a language > model which does not take into account the order in which the words > appear in an ngram, so if you have the string 'police chief of' in your > model, you will get a result for both 'chief of police' and 'police > chief of'. I have thought of using IRSTLM or some generic model and > scoring all the permutations, but wondered if there was a more efficient > implementation already in existence. I have searched without much luck > in Google, but perhaps I am searching with the wrong words. > > Best regards, > > Fran > > ___ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support > ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] bag of words language model
i implemented this years ago (the idea then was to see if for free-word-order languages, phrases could be generalised). at the time it didn't seem that there was a more efficient way to do it than just generate permutations and score them. and if you think about it, this is essentially the reordering problem Miles On 25 October 2010 12:59, Philipp Koehn wrote: > Hi, > > I am not familiar with that, but somewhat related is > Arne Mauser's global lexical model, which also exists > as a secret feature in Moses (secret because no > effiencient training exists): > > Citation: > A. Mauser, S. Hasan, and H. Ney. Extending Statistical Machine > Translation with Discriminative and Trigger-Based Lexicon Models. In > Conference on Empirical Methods in Natural Language Processing > (EMNLP), Singapore, August 2009. > http://www-i6.informatik.rwth-aachen.de/publications/download/628/MauserArneHasanSav%7Bs%7DaNeyHermann--ExtendingStatisticalMachineTranslationwithDiscriminativeTrigger-BasedLexiconModels--2009.pdf > > -phi > > > On Fri, Oct 22, 2010 at 7:02 PM, Francis Tyers wrote: >> Hello all, >> >> I have a rather strange request. Does anyone know of any papers (or >> impementations) on bag-of-words language models ? That is, a language >> model which does not take into account the order in which the words >> appear in an ngram, so if you have the string 'police chief of' in your >> model, you will get a result for both 'chief of police' and 'police >> chief of'. I have thought of using IRSTLM or some generic model and >> scoring all the permutations, but wondered if there was a more efficient >> implementation already in existence. I have searched without much luck >> in Google, but perhaps I am searching with the wrong words. >> >> Best regards, >> >> Fran >> >> ___ >> Moses-support mailing list >> Moses-support@mit.edu >> http://mailman.mit.edu/mailman/listinfo/moses-support >> > ___ > 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. > > -- 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
Re: [Moses-support] bag of words language model
Hi, Philipp, I was wondering what that secret model was... Is there any brief documentation of what the Moses code expects to load for this model? The training of this discriminative word lexicon can be heavily parallelized. Is there any such implementation available, despite not being efficient enough? Cheers, O. Philipp Koehn wrote: > Hi, > > I am not familiar with that, but somewhat related is > Arne Mauser's global lexical model, which also exists > as a secret feature in Moses (secret because no > effiencient training exists): > > Citation: > A. Mauser, S. Hasan, and H. Ney. Extending Statistical Machine > Translation with Discriminative and Trigger-Based Lexicon Models. In > Conference on Empirical Methods in Natural Language Processing > (EMNLP), Singapore, August 2009. > http://www-i6.informatik.rwth-aachen.de/publications/download/628/MauserArneHasanSav%7Bs%7DaNeyHermann--ExtendingStatisticalMachineTranslationwithDiscriminativeTrigger-BasedLexiconModels--2009.pdf > > -phi > > > On Fri, Oct 22, 2010 at 7:02 PM, Francis Tyers wrote: >> Hello all, >> >> I have a rather strange request. Does anyone know of any papers (or >> impementations) on bag-of-words language models ? That is, a language >> model which does not take into account the order in which the words >> appear in an ngram, so if you have the string 'police chief of' in your >> model, you will get a result for both 'chief of police' and 'police >> chief of'. I have thought of using IRSTLM or some generic model and >> scoring all the permutations, but wondered if there was a more efficient >> implementation already in existence. I have searched without much luck >> in Google, but perhaps I am searching with the wrong words. >> >> Best regards, >> >> Fran >> >> ___ >> Moses-support mailing list >> Moses-support@mit.edu >> http://mailman.mit.edu/mailman/listinfo/moses-support >> > ___ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
[Moses-support] Moses use by translation industry
Hi, not a bug, but a feature: TDA Members doing business with Moses The translation industry is steadily appropriating the Moses translation engine, an open source system available as a kit on the web. At the TAUS User Conference 2010 in Portland (Oregon) TDA members from major corporations and service vendors gave first-time accounts to the community of their experience with this MT engine. Here are the highlights. http://www.tausdata.org/blog/2010/10/doing-business-with-moses-open-source-translation/ -phi ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] bag of words language model
Hi, I added the training script and some documentation: http://www.statmt.org/mosesdev/?n=Moses.AdvancedFeatures#ntoc25 Let me know, if this actually works. -phi On Mon, Oct 25, 2010 at 1:15 PM, Ondrej Bojar wrote: > Hi, Philipp, > > I was wondering what that secret model was... Is there any brief > documentation of what the Moses code expects to load for this model? > > The training of this discriminative word lexicon can be heavily > parallelized. Is there any such implementation available, despite not > being efficient enough? > > Cheers, O. > > Philipp Koehn wrote: >> Hi, >> >> I am not familiar with that, but somewhat related is >> Arne Mauser's global lexical model, which also exists >> as a secret feature in Moses (secret because no >> effiencient training exists): >> >> Citation: >> A. Mauser, S. Hasan, and H. Ney. Extending Statistical Machine >> Translation with Discriminative and Trigger-Based Lexicon Models. In >> Conference on Empirical Methods in Natural Language Processing >> (EMNLP), Singapore, August 2009. >> http://www-i6.informatik.rwth-aachen.de/publications/download/628/MauserArneHasanSav%7Bs%7DaNeyHermann--ExtendingStatisticalMachineTranslationwithDiscriminativeTrigger-BasedLexiconModels--2009.pdf >> >> -phi >> >> >> On Fri, Oct 22, 2010 at 7:02 PM, Francis Tyers wrote: >>> Hello all, >>> >>> I have a rather strange request. Does anyone know of any papers (or >>> impementations) on bag-of-words language models ? That is, a language >>> model which does not take into account the order in which the words >>> appear in an ngram, so if you have the string 'police chief of' in your >>> model, you will get a result for both 'chief of police' and 'police >>> chief of'. I have thought of using IRSTLM or some generic model and >>> scoring all the permutations, but wondered if there was a more efficient >>> implementation already in existence. I have searched without much luck >>> in Google, but perhaps I am searching with the wrong words. >>> >>> Best regards, >>> >>> Fran >>> >>> ___ >>> Moses-support mailing list >>> Moses-support@mit.edu >>> http://mailman.mit.edu/mailman/listinfo/moses-support >>> >> ___ >> Moses-support mailing list >> Moses-support@mit.edu >> http://mailman.mit.edu/mailman/listinfo/moses-support > ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
[Moses-support] train-truecaser.perl proposed tweak
Hi, Are truecase models still widely in use? I have a proposal for a tweak to the train-truecaser.perl script. Currently, we don't take the first token of a sentence as evidence for the true casing of that type, on the basis that the first word of a sentence is always capitalized. The first token of a segment is always assumed to be the first word of a sentence, and thus is never taken as casing evidence. However, if a given segment is only one token long, then the segment is probably not a sentence, and the token is quite possibly in its natural case. So my proposal is to take the sole token of one-token segments as evidence for true casing. I attach the code change. Any objections? If not, I'll check it in. Ben train-truecaser.perl Description: Binary data ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] train-truecaser.perl proposed tweak
this sounds risky to me. it would be better to allow the user to specify the behaviour; for your suggestions, you would add an extra flag which would enable this. the default would be for truecasing to operate as it used to. Miles On 25 October 2010 17:37, Ben Gottesman wrote: > Hi, > > Are truecase models still widely in use? > > I have a proposal for a tweak to the train-truecaser.perl script. > > Currently, we don't take the first token of a sentence as evidence for the > true casing of that type, on the basis that the first word of a sentence is > always capitalized. The first token of a segment is always assumed to be > the first word of a sentence, and thus is never taken as casing evidence. > > However, if a given segment is only one token long, then the segment is > probably not a sentence, and the token is quite possibly in its natural > case. So my proposal is to take the sole token of one-token segments as > evidence for true casing. > > I attach the code change. > > Any objections? If not, I'll check it in. > > Ben > > ___ > 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
Re: [Moses-support] train-truecaser.perl proposed tweak
Hi, Sounds reasonable to me, but it would be good to have this as an option, as Miles suggested. -phi On 25 Oct 2010 17:40, "Ben Gottesman" wrote: > Hi, > > Are truecase models still widely in use? > > I have a proposal for a tweak to the train-truecaser.perl script. > > Currently, we don't take the first token of a sentence as evidence for the > true casing of that type, on the basis that the first word of a sentence is > always capitalized. The first token of a segment is always assumed to be > the first word of a sentence, and thus is never taken as casing evidence. > > However, if a given segment is only one token long, then the segment is > probably not a sentence, and the token is quite possibly in its natural > case. So my proposal is to take the sole token of one-token segments as > evidence for true casing. > > I attach the code change. > > Any objections? If not, I'll check it in. > > Ben ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support