Hi,
I'm getting the following PhraseScore error when training an En->FR engine, in
my centos (RedHad) Linux environment.
>>
(6) score phrases @ Thu May 7 12:19:52 CEST 2009
(6.1) sorting f2e @ Thu May 7 12:19:52 CEST 2009
Executing: gunzip < ./model/extract.gz | LC_ALL=C sort -T ./model > ./model/extr
act.sorted
(6.2) creating table half ./model/phrase-table.half.f2e @ Thu May 7 12:41:38 C
EST 2009
Executing: /usr/bin/training/phrase-extract/score ./model/extract.sorted ./model
/lex.f2e ./model/phrase-table.half.f2e
/usr/bin/training/phrase-extract/score ./model/extract.sorted ./model/lex.f2e ./
model/phrase-table.half.f2e
PhraseScore v1.4 written by Philipp Koehn
phrase scoring methods for extracted phrases
Loading lexical translation table from ./model/lex.f2eline 2 in ./model/lex.f2e
has wrong number of tokens, skipping:
0 ERROR: Execution of: /usr/bin/training/phrase-extract/score ./model/extract.so
rted ./model/lex.f2e ./model/phrase-table.half.f2e
died with signal 11, without coredump
<<
During phase 5, I noticed a long list of warnings ("sentence xxx has alignment
point (x, x) out of bounds (x, x)"), which I don't recall seeing in previous
trainings. Could this be related?
(Note that I have successfully trained several engines in that same environment
beforehand, against subsets of the same corpus)
Thanks,
Mirko
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
