Hieu Hoang
99b4b63c0c
change signature of GetChartRuleCollection()
2015-01-07 12:59:08 +04:00
Nicola Bertoldi
e4eb201c52
merged master into dynamic-models and solved conflicts
2014-12-13 12:52:47 +01:00
Phil Williams
5240c430ce
Merge s2t branch
...
This adds a new string-to-tree decoder, which can be enabled with the -s2t
option. It's intended to be faster and simpler than the generic chart
decoder, and is designed to support lattice input (still WIP). For a en-de
system trained on WMT14 data, it's approximately 40% faster in practice.
For background information, see the decoding section of the EMNLP tutorial
on syntax-based MT:
http://www.emnlp2014.org/tutorials/5_notes.pdf
Some features are not implemented yet, including support for internal tree
structure and soft source-syntactic constraints.
2014-11-04 13:13:56 +00:00
Rico Sennrich
a128ad1847
n-best-tree output needs trees for unknown words
2014-10-21 09:51:20 +01:00
Hieu Hoang
efa5befb16
method rename
2014-08-08 15:59:34 +01:00
Hieu Hoang
23f10cc73f
move notice about czech prefixes to share/README
2014-08-06 15:03:37 +01:00
Hieu Hoang
e863592f40
TargetPhrase to have pointer to the phrase table that creates it
2014-08-04 19:28:04 +01:00
Nicola Bertoldi
2f3cd5e2fe
beautify
2014-05-19 15:34:27 +02:00
Nicola Bertoldi
20381cbf89
merged master into dynamic-models and solved conflicts
2014-04-28 19:18:38 +02:00
Rico Sennrich
45630a5851
various optimizations to make CYK+ parser several times faster and eat less memory.
...
speed-up of decoding depends on how much time is spent in parser:
10-50% speed-up for string-to-tree systems observed (more on long sentences and with high max-chart-span).
if you only use hiero or string-to-tree models (but none with source syntax), use compile-option --unlabelled-source for (small) efficiency gains.
2014-03-21 11:12:24 +00:00
Phil Williams
04dbd3c7aa
moses_chart: more efficient scope-3 parsing if sentence length < max-chart-span
2014-03-14 08:49:09 +00:00
Rico Sennrich
c27ecbe5c6
rename SyntaxConstraintFeature to TreeStructureFeature
...
(makes it clearer what it does; build/print the internal tree structure in string-to-tree decoding)
no longer rely on name of FF for printing internal trees
2014-03-03 13:56:19 +00:00
Nicola Bertoldi
bd83999264
beautify
2014-01-15 16:42:02 +01:00
Hieu Hoang
ebc6e59b17
consistent global variable g_mosesDebug
2013-12-11 19:04:42 +00:00
Hieu Hoang
ba209202ef
move all feature functions out of StaticData
2013-12-07 00:21:06 +00:00
Hieu Hoang
3c0eaac9a3
replace CHECK with UTIL_THROW_IF in Moses
2013-11-21 14:55:41 +00:00
Hieu Hoang
2f00ae936b
move collection of phrase-table from Staticdata to PhraseDictionary
2013-11-15 17:26:26 +00:00
Matthias Huck
c94c998f63
internal tree structure in chart decoder: use square brackets for OOVs as well
2013-11-13 18:31:15 +00:00
Phil Williams
69f5e4bec3
Merge branch 'master' into GHKMStruct
2013-10-09 16:21:49 +01:00
Hieu Hoang
f18e35c42a
correct creation of input paths for lattices
2013-10-03 18:58:45 +01:00
Hieu Hoang
6759af3821
beautify
2013-10-03 11:33:48 +01:00
Hieu Hoang
6ccc17b804
speed up compiling by removing headers from StaticData.h
2013-10-03 11:05:53 +01:00
Phil Williams
2a28d1a73e
Merge branch 'master' into GHKMStruct
...
Conflicts:
moses-chart-cmd/IOWrapper.cpp
moses-chart-cmd/IOWrapper.h
moses/FF/Factory.cpp
moses/Parameter.cpp
moses/StaticData.h
phrase-extract/extract-ghkm/ScfgRuleWriter.cpp
phrase-extract/score-main.cpp
2013-09-29 15:27:09 +01:00
Hieu Hoang
9e890479a2
get ready to do lattice for scfg
2013-09-28 19:06:04 +01:00
Hieu Hoang
31ce9b510e
beautify
2013-09-27 09:35:24 +01:00
maria nadejde
3c441bdaa3
Merge branch 'GHKMStruct' of github.com:moses-smt/mosesdecoder into GHKMStruct
2013-09-13 18:18:52 +02:00
maria nadejde
48fa62838c
Merge branch 'master' into GHKMStruct
2013-09-13 17:30:50 +02:00
Matthias Huck
c39bed60c0
Tree fragments in GHKM glue rules;
...
output of LHS tag in tree fragments for UNKs;
GHKMParse info is now denoted as Tree info
2013-09-13 17:10:21 +02:00
Hieu Hoang
3b03d803d9
make sure Evaluate(inputPath) is called for chart translation options
2013-09-13 09:27:48 +02:00
Matthias Huck
225f33e325
tiny changes to GHKMParse info in search
2013-09-12 17:37:54 +02:00
Hieu Hoang
af74ee1968
delete duplicate m_inputPathMatrix in TranslationOptionList
2013-08-13 11:44:58 +01:00
Hieu Hoang
441acf15e6
beautify
2013-08-07 14:18:12 +01:00
Hieu Hoang
a1f5167f85
get ready to delete source phrase from TargetPhrase class
2013-08-07 11:37:40 +01:00
Hieu Hoang
d395737639
minor cleanup
2013-08-02 18:24:36 +01:00
Hieu Hoang
afcf65098f
parsing doesn't depend on input sentence anymore
2013-08-02 18:09:47 +01:00
Hieu Hoang
0596c3e9e4
Add NonTerminalSet variable to InputPath
2013-08-02 15:54:49 +01:00
Hieu Hoang
ba187294d5
begin cleanup of SCFG parsing. Get rid of Sentence variable in ChartRuleLookupManager, replace with ChartParser variable
2013-07-31 12:25:34 +01:00
Hieu Hoang
77872f7521
beautify
2013-07-30 15:04:37 +01:00
Hieu Hoang
1d40a604df
create queue of InputPath objects. Starting SCFG parsing with lattices and conf net
2013-07-30 15:03:47 +01:00
Hieu Hoang
69acbfa1d3
compiles, but only on eclipse
2013-06-24 14:45:20 +01:00
Hieu Hoang
6249432407
beautify
2013-05-29 18:16:15 +01:00
Hieu Hoang
ae82d02a05
delete sourcePhrase variable in TargetPhrase class
2013-05-28 00:41:25 +01:00
Hieu Hoang
49e69f19e2
split classes in DummyScoreProducers into separate files
2013-05-25 00:25:20 +01:00
Hieu Hoang
a80d838b0f
move feature functions into moses/FF
2013-05-24 18:02:49 +01:00
Hieu Hoang
f4a75b30f7
Make lhsTarget a pointer
2013-05-22 11:22:17 +01:00
Hieu Hoang
499487fb98
get rid of TargetPhrase::SetScore. Expose ScorerBreakdown object so they can be set directly
2013-05-13 15:36:09 +01:00
Hieu Hoang
981351758a
delete class TranslationSystem
2013-05-11 14:13:26 +01:00
Hieu Hoang
ce95c117f6
merge
2013-04-29 18:46:48 +01:00
Kenneth Heafield
f1d3663810
Back FactorCollection with a memory pool. Less memory for large vocabularies.
2013-04-25 19:42:30 +01:00
Hieu Hoang
b53b93f09f
gt rid of word penalty of 0.434. Adjust weight accordingly
2013-04-24 19:23:14 +01:00
