the windows version uses the built in language model which only goes up to
trigrams.

there's an assert, however, will make sure it aborts to avoid confusion

2008/7/8 Pham Thi Anh Vi <[EMAIL PROTECTED]>:

> Hi Mr. Hieu,
> Here is my moses config file. I use this config file (LM, phrase-table,
> reordering) on both Window SP2 and Fedora C5 and found that problem. So
> could you please tell me why the diference happens?
> Thanks,
> ########################
> ### MOSES CONFIG FILE ###
> #########################
> # input factors
> [input-factors]
> 0
>
> # mapping steps
> [mapping]
> 0 T 0
>
> # translation tables: source-factors, target-factors, number of scores,
> file
> [ttable-file]
> 0 0 5
> /home/zil/Working/Language_models/Rbtdfinal_280k/model_srilm/phrase-table.0-0.gz
>
> # no generation models, no generation-file section
>
> # language models: type(srilm/irstlm), factors, order, file
> [lmodel-file]
> 0 0 5 /home/zil/Working/Language_models/Rbtdfinal_280k/lm/GwtwVnthuquan.lm
>
>
> # limit on how many phrase translations e for each phrase f are loaded
> # 0 = all elements loaded
> [ttable-limit]
> 20
> 0
> # distortion (reordering) files
> [distortion-file]
> 0-0 msd-bidirectional-fe 6
> /home/zil/Working/Language_models/Rbtdfinal_280k/model_srilm/reordering-table.msd-bidirectional-fe.0.5.0-0.gz
>
> # distortion (reordering) weight
> [weight-d]
> 0.3
> 0.3
> 0.3
> 0.3
> 0.3
> 0.3
> 0.3
>
> # language model weights
> [weight-l]
> 0.5000
>
>
> # translation model weights
> [weight-t]
> 0.2
> 0.2
> 0.2
> 0.2
> 0.2
>
> # no generation models, no weight-generation section
>
> # word penalty
> [weight-w]
> -1
>
> [distortion-limit]
> 6
>
> On Mon, Jul 7, 2008 at 3:25 PM, Hieu Hoang <[EMAIL PROTECTED]>
> wrote:
>
>> can u send me your ini file. i'll take a look
>>
>>
>> *Pham Thi Anh Vi <[EMAIL PROTECTED]>* wrote:
>>
>>  Hi all,
>> I have run decoder on both Window XP SP 2 and Fedora C7. I used the same
>> training model (phrase-table, language model, reordering, ...) when run
>> decoder on each OS. But the results I received is different from each other.
>> Ex : I run moses with input sentence : "I love you". The output sentence I
>> received :
>>     - On Window : "Tôi tình yêu cô"
>>     - On Fedora : "Tôi yêu cô"
>> The translation sentence quality received when running decoder on Fedora
>> is better than does on Window.
>> Why there is different between running decoder on Window and Fedora?
>> Could you help me to explain about this problem!
>> Best Regards,
>> _______________________________________________
>> Moses-support mailing list
>> [email protected]
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>>
>>
>> Hieu Hoang
>> http//www.hoang.co.uk/hieu
>>
>> ------------------------------
>> Not happy with your email address?
>>  Get the one you really want <http://uk.docs.yahoo.com/ymail/new.html> -
>> millions of new email addresses available now at 
>> Yahoo!<http://uk.docs.yahoo.com/ymail/new.html>
>>
>
>
>
>
>
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to