Revision 9e61900fad22c87341b4690c202c57f083eb1402 authored by mfederico on 04 August 2008, 13:06:52 UTC, committed by mfederico on 04 August 2008, 13:06:52 UTC
Now, the penalty for out-of-vocabulary words is specified by the parameter -lmodel-dub: dictionary upper bounds of language models For instance, if you set it lmodel-dub to 1000000 (1M) and your actual vocabulary is let me say 200000 (200K), then the LM probabilty of the OOV word-class is divided by 800000 (800K), i.e. 1M-200K You have to make sure that lmodel-dub is always larger than the LM dictionary. git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@1870 1f5c12ca-751b-0410-a591-d2e778427230
1 parent 7a2ebed
File | Mode | Size |
---|---|---|
hypergraph-prototype | ||
mert | ||
misc | ||
moses | ||
moses-cmd | ||
regression-testing | ||
report | ||
reranking | ||
scripts | ||
sigtest-filter | ||
web | ||
BUILD-INSTRUCTIONS.txt | -rw-r--r-- | 3.1 KB |
Makefile.am | -rw-r--r-- | 223 bytes |
config.h.in | -rw-r--r-- | 1.4 KB |
configure.in | -rw-r--r-- | 2.3 KB |
depcomp | -rwxr-xr-x | 12.6 KB |
install-sh | -rwxr-xr-x | 6.2 KB |
ltmain.sh | -rw-r--r-- | 178.0 KB |
make-release-tarball.sh | -rwxr-xr-x | 1.4 KB |
missing | -rwxr-xr-x | 10.0 KB |
mkinstalldirs | -rwxr-xr-x | 1.9 KB |
regenerate-makefiles.sh | -rwxr-xr-x | 858 bytes |
validate_more_revisions.sh | -rwxr-xr-x | 900 bytes |
validate_revision.sh | -rwxr-xr-x | 1.3 KB |
Computing file changes ...