Hi Hieu,
According to experiment.meta, the flow is:
* Decoding produces system-output
* system-output goes through the remove-markup and then recase-output or
detruecase-output processes to produce recased-output
* recased-output goes through the detokenize-output process to produce
detokenized
Hi John,
my guess would be that one of your files isn't tokenized -- does that
language you're working on have word boundaries?
The -e option of mteval does just what you described -- encloses
non-ascii characters between spaces. The way I see it, if the alphabet
of your language is mostly non-as
Following Barry's introduction of TranslationSystem.cpp in r3394, the Moses
"Adding Feature Functions" tutorial (
http://www.statmt.org/moses/?n=Moses.FeatureFunctions) needs to be updated.
I just hit my head against this while attempting to bring my syntactic LM
branch up to date with trunk.
Nam
Hi,
> Thank you for replying to my mail. Yes, I have thought about this solution
> for alignments, but the heuristics used in moses got me thinking, and I
> wanted to use the heuristic to obtain the final alignments(since the
> alignments are of a higher quality). So, my question would be more lik
Hi Sir,
Thank you for replying to my mail. Yes, I have thought about this solution
for alignments, but the heuristics used in moses got me thinking, and I
wanted to use the heuristic to obtain the final alignments(since the
alignments are of a higher quality). So, my question would be more like,
Hi,
> I am familiar with the architecture of Moses, and know that the 2nd and 3rd
> steps involve computing alignments in both directions while the 4th step
> applies the heuristic(grow,union ...) to obtain the final alignments. These
> alignments are further used to extract the phrase-pairs. Now
Thanks Mark,
My results are still off.
My data is encoded in utf-8.
Your script reports an actual BLEU score of 0.024447 for my hypothesis 1.
The score reported by mteval using the -e option is 0.2459.
The score reported by mteval without the -e option is 0.0268.
I'm not sure which score is more ac
Hi!
I used to tune with the old mert-moses.pl, in which "distinct" is
hard-coded in the cmd to be passed to the decoder; now I switch to the
new mert-moses.pl and find that it is removed.
The result is that nbest list becomes not as diverse and my tuning
bleu is consistently down by 1 bleu point,
Hi,
Great! I added my .cpp and h. files in Makefile.am and everything works fine
now.
Thanks a lot and best regards
Fabienne
On Fri, Nov 26, 2010 at 7:04 PM, Barry Haddow wrote:
> Hi Fabienne
>
> Did you add your .cpp file to Makefile.am, and regenerate makefiles?
> Double-check that you've
Hi John,
Thanks for pointing out the issue; I added support for arbitrary
encodings to the script, by default it's set to UTF8 but you can
change the global variable on line 23 for other encodings; just update
the file from SVN.
Treating non-ascii characters as separate tokens by wrapping them in
10 matches
Mail list logo
