Thanks, Kenneth,

After updating to the latest revision (3873) the differences in BLEU 
disappeared. My bad for not updating before posting. However, this confirms 
there was a bug.

Regards,
Karlis

> 
> 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