Just to get the word out more, trie is broken before 3847 for common
pruning strategies as announced in "[Moses-support] kenlm updated in
3847".  Admittedly the subject could have yelled more, but it's also
easy to miss posts.

On 02/07/11 11:11, Kārlis Goba wrote:
> Thanks, Kenneth,
> 
> This was revision 3796, I will try with a newer version. 
> 
>> Hi,
>>
>>      What revision of Moses are you using?  Does this still happen
>> after you
>> run svn up and recompile Moses?
>>
>> Kenneth
>>
>> On 02/07/11 10:53, Kārlis Goba wrote:
>>> Hi,
>>>
>>> My preferred way to build large LMs has been IRSTLM as it can handle
>> large corpora nicely by splitting the task. The produced binary LMs
>> work well with Moses. Then I decided to try the new and shiny KenLM.
>> However, when converting the result to KenLM format, the converted LM
>> gives a lot worse BLEU score.
>>>
>>> I am building the LMs in this way:
>>>
>>> 1) build-lm.sh - build iARPA LM
>>> 2) prune-lm
>>> 3) compile-lm - convert iARPA to binary IRSTLM (gives me 0.3346 BLEU)
>>> 4) compile-lm --text=yes - convert iARPA to ARPA
>>> 5) build_binary trie - convert ARPA to KenLM (gives me 0.2543 BLEU)
>>>
>>> The moses.ini for both cases is the same, differing only in the LM
>> line (1 0 5 "/mnt/smt/lm/mt4-lv-lcase/lm-pruned.blm" vs "8 0 5
>> /mnt/smt/lm/mt4-lv-lcase/lm-pruned.mmap"). I have observed this in more
>> than one case.
>>>
>>> I don't know who blame - either the conversion from iARPA to ARPA or
>> KenLM.
>>>
>>> What is your best practice for estimating large LMs to be converted
>> to KenLM? Is it SRILM?
>>>
>>> --
>>> Karlis
>>>
>>> _______________________________________________
>>> Moses-support mailing list
>>> [email protected]
>>> http://mailman.mit.edu/mailman/listinfo/moses-support
>> _______________________________________________
>> Moses-support mailing list
>> [email protected]
>> http://mailman.mit.edu/mailman/listinfo/moses-support
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to