Hi,
I have a problem decoding a long sentence (90 Segments/Words) during
tuning, Decoding will go smooth for 5 iterations and after that the decoder
keep growing in memory. For those familiar with NIST -MT03 Arabic, it is
sentence 602 , it is originally 53 words but since I am using segmented
version it became 90 words.
Problem is reproducible even if I stopped the tuning and restarted again
with latest run?.moses.ini.
Thanks in advance for your feedback,
Mohamed
# 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 /path/phrase-table.0-0.1
# no generation models, no generation-file section
# language models: type(srilm/irstlm), factors, order, file
[lmodel-file]
1 0 5 /path/LM.blm
# 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
/path/reordering-table.msd-bidirectional-fe.0.5.0-0
# distortion (reordering) weight
[weight-d]
0.033399
0.034414
0.089844
0.153478
0.102058
-0.061896
0.185453
# language model weights
[weight-l]
0.087339
# translation model weights
[weight-t]
0.020556
0.040513
0.050062
0.031836
0.013342
# no generation models, no weight-generation section
# word penalty
[weight-w]
-0.095811
[distortion-limit]
6
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
