Hi Nakul, 

"i get UNK for all types of words/senteces which i
translate." 

Looks like you want Hindi as your source language and
English as you target langauge. Double-check to make sure Hindi is your
source language in your training corpus and train-model.perl 

An easy
test for this would be to translate an English phrase and see if moses
outputs Hindi. 

Tom 

On Tue, 1 Mar 2011 16:36:08 +0530, nakul sharma 
wrote:  

Hi All,

i have tuned the moses decoder sucessfully and now
trying to see if it works fine.

i am executing the moses executable
file as follows:-

echo "यह"|
/home/nakul/Desktop/smt_sw/moses-2010-08-13_1/moses/moses-cmd/src/moses
-f model/moses.ini

i get output:-

Search took 0.000 seconds
यह 
BEST
TRANSLATION: यह|UNK|UNK|UNK [1] [total=-105.384]  
 Translation took
0.000 seconds
Finished translating

i get UNK for all types of
words/senteces which i translate.

the contents of moses file in
model/moses.ini are as follows:-

#########################
 ### MOSES
CONFIG FILE ###
#########################

# input
factors
[input-factors]
0

# mapping steps
[mapping]
0 T 0

#
translation tables: table type (hierarchical(0), textual (0), binary
(1)), source-factors, target-factors, number of scores, file 
 # OLD
FORMAT is still handled for back-compatibility
# OLD FORMAT translation
tables: source-factors, target-factors, number of scores, file 
# OLD
FORMAT a binary table type (1) is assumed 
[ttable-file]
0 0 0 5
/home/nakul/Desktop/smt_sw/moses-2010-08-13_1/moses/scripts/training/moses-cripts/scripts-20110207-1952/training/model/phrase-table.gz

#
no generation models, no generation-file section

# language models:
type(srilm/irstlm), factors, order, file
[lmodel-file]
0 0 3
/home/nakul/Desktop/srilm/bin/i686/Englm.lm

# limit on how many phrase
translations e for each phrase f are loaded
 # 0 = all elements
loaded
[ttable-limit]
20

# distortion (reordering)
files
[distortion-file]
0-0 wbe-msd-bidirectional-fe-allff 6
/home/nakul/Desktop/smt_sw/moses-2010-08-13_1/moses/scripts/training/moses-cripts/scripts-20110207-1952/training/model/reordering-table.wbe-msd-bidirectional-fe.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

i there some problem here
which is leading to incorrect translation ? or i am going wrong while
tuning decoder ?
 Sorry for long mail but i thought it may be necessary
to find out errors.

With Warm Regards,
nakul.

 
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to