diff options
author | Ulrich Germann <ugermann@inf.ed.ac.uk> | 2014-08-04 20:20:33 +0400 |
---|---|---|
committer | Ulrich Germann <ugermann@inf.ed.ac.uk> | 2014-08-04 20:20:33 +0400 |
commit | ef307b29c206747778ab959286b50f57ede8bace (patch) | |
tree | 16d16154af82257cd7fd7162ef7ea3338e68b080 | |
parent | 2711360ce7cddc24761c207a9fbba1ec36eb3d2d (diff) |
Replaced content by pointer to online documentation.
-rw-r--r-- | doc/PhraseDictionaryBitextSampling.howto | 33 |
1 files changed, 3 insertions, 30 deletions
diff --git a/doc/PhraseDictionaryBitextSampling.howto b/doc/PhraseDictionaryBitextSampling.howto index 143a634ed..69ab11b5b 100644 --- a/doc/PhraseDictionaryBitextSampling.howto +++ b/doc/PhraseDictionaryBitextSampling.howto @@ -1,31 +1,4 @@ -How to use memory-mapped suffix array phrase tables in the moses decoder -(phrase-based decoding only) - -1. Compile with the bjam switch --with-mm - -2. You need - - sentences aligned text files - - the word alignment between these files in symal output format - -3. Build binary files - - Let - ${L1} be the extension of the language that you are translating from, - ${L2} the extension of the language that you want to translate into, and - ${CORPUS} the name of the word-aligned training corpus - - % zcat ${CORPUS}.${L1}.gz | mtt-build -i -o /some/path/${CORPUS}.${L1} - % zcat ${CORPUS}.${L2}.gz | mtt-build -i -o /some/path/${CORPUS}.${L2} - % zcat ${CORPUS}.${L1}-${L2}.symal.gz | symal2mam /some/path/${CORPUS}.${L1}-${L2}.mam - % mmlex-build /some/path/${CORPUS} ${L1} ${L2} -o /some/path/${CORPUS}.${L1}-${L2}.lex -c /some/path/${CORPUS}.${L1}-${L2}.coc - -4. Define line in moses.ini - - The best configuration of phrase table features is still under investigation. - For the time being, try this: - - PhraseDictionaryBitextSampling name=PT0 output-factor=0 num-features=9 path=/some/path/${CORPUS} L1=${L1} L2=${L2} pfwd=g pbwd=g smooth=0 sample=1000 workers=1 - - You can increase the number of workers for sampling (a bit faster), - but you'll lose replicability of the translation output. +The documentation for memory-mapped, dynamic suffix arrays has moved to + http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc40 +Search for PhraseDictionaryBitextSampling. |