Commit Graph

188 Commits

Author SHA1 Message Date
Matthias Huck
01bed83cf9 GHKM extraction: option to strip non-terminal labels from BitPar syntactic parses right during extraction (i.e., remove any suffix starting with a hyphen from the label) 2015-03-10 21:25:32 +00:00
Phil Williams
9e2eb702dc EMS: add TRAINING:use-syntax-input-weight-feature option 2015-03-10 11:40:49 +00:00
Phil Williams
7eba58b942 EMS: add TRAINING:dont-tune-glue-grammar option
Adds -dont-tune-glue-grammar to train-model.perl command during config file
generation step.  This is preferable to manually adding -dont-tune-glue-grammar
to TRAINING:training-options because changing its value won't trigger a re-run
of dependent steps that don't really need re-running (like word alignment).
2015-03-10 10:20:19 +00:00
Matthias Huck
25f5470216 GHKM: write target parts-of-speech as a factor 2015-03-09 21:54:03 +00:00
Matthias Huck
06e87d851e GHKM: extract POS phrase property (from preterminals in the syntactic parse tree) 2015-03-04 21:40:56 +00:00
Phil Williams
90e8d4940c EMS: add TRAINING:no-glue-grammar option 2015-03-03 12:36:09 +00:00
Philipp Koehn
2638ff0480 added thot to EMS 2014-10-14 10:13:16 -04:00
Philipp Koehn
acefdb0262 bug fix for final-step 2014-09-21 05:59:21 +01:00
Philipp Koehn
a574454635 bug fix with delete crashed step output files 2014-08-14 14:14:42 -04:00
Philipp Koehn
7a087f24df also delete interrupted steps 2014-08-14 10:15:58 -04:00
Matthias Huck
c27cbf55ea source labels: integration into EMS 2014-08-07 21:02:51 +01:00
Matthias Huck
3a5dee12e8 implementation of phrase orientation in GHKM extraction
(...but a corresponding feature function for the chart-based decoder has not been written yet)
2014-07-28 18:27:12 +01:00
phikoehn
2d11fe3916 Merge branch 'master' of ssh://github.com/moses-smt/mosesdecoder 2014-07-23 15:40:04 +01:00
phikoehn
2239501b21 allow specification of weights for lm interpolation 2014-07-23 15:39:42 +01:00
Philipp Koehn
55ae15a6f8 integration of Uli Germann's memory mapped suffix array phrase table into EMS 2014-07-22 10:12:14 -04:00
Matthias Huck
c2644c9a08 typo in log output 2014-06-16 15:10:53 +01:00
phikoehn
45648d03b9 support for lmplz training of osm in ems 2014-06-11 13:44:02 +01:00
phikoehn
9a91f423e4 fixed error 2014-05-30 08:30:06 +01:00
Hieu Hoang
9615f4636c change error to warning. Seems to work ok with recaser 2014-05-30 05:40:22 +01:00
Philipp Koehn
1b26f37f9a allow specification of final step and final outcome in experiment.perl 2014-05-28 03:58:14 -04:00
Philipp Koehn
85ea9d552a fixes to delete-crashed and delete-run 2014-05-23 15:01:53 -04:00
Philipp Koehn
dd9a59499f progress on deleting steps and runs 2014-05-21 11:16:40 -04:00
Philipp Koehn
aac51cec89 ems: delete a run. may work. 2014-05-16 16:57:34 -04:00
Your Name
93d2d19c3e delete crashed steps 2014-05-08 16:42:11 -04:00
Nadir Durrani
5e3e50d4ec In-Decoding Transliteration Module 2014-04-16 17:28:49 +01:00
Rico Sennrich
c8682e9420 target-syntax: use SoftMatchingFeature to assign non-terminal to unknown words 2014-03-24 14:57:24 +00:00
Phil Williams
cea86d6750 Transliteration support for syntax models. 2014-03-21 22:13:38 +00:00
Hieu Hoang
c501e5fab6 accidental error in perl script 2014-03-14 09:04:49 +00:00
Nadir Durrani
054a648713 Transliteration Script - Modifications 2014-03-13 13:10:38 +00:00
phikoehn
049be8b71c Merge branch 'master' of ssh://github.com/moses-smt/mosesdecoder 2014-02-12 21:01:09 +00:00
phikoehn
d6b62db5b1 fix bug if interpolated lm on different factors 2014-02-12 21:00:55 +00:00
Matthias Huck
65811a0325 tree fragments: tiny issues with the extraction pipeline 2014-02-03 18:13:10 +00:00
Hieu Hoang
6a10f8ce71 corrected phrase-table name / type mixup when creating filtering script 2014-01-23 17:09:56 +00:00
Hieu Hoang
ebc724b3de Merge branch 'master' of github.com:moses-smt/mosesdecoder 2014-01-12 13:51:04 +00:00
Hieu Hoang
a975e3d32d Add Exception as a keyword for detecting error in EMS step 2014-01-12 13:50:01 +00:00
phikoehn
25553079d9 bug fix with sparse feature handling depending on word alignment in compact phrase table 2014-01-10 18:34:47 +00:00
phikoehn
9ea0f5dd0e reporting on init (pretty slow for binary phrase table!) and bug fix in experiment.perl with setting filter settings 2014-01-05 22:39:47 +00:00
phikoehn
c8b5cc4f0e avoid warning; 2013-12-31 19:21:28 +00:00
Nadir Durrani
7f75018349 Post-decoding Transliteration Script 2013-12-18 16:10:57 +00:00
Nadir Durrani
c291f859a0 Transliteration Mining 2013-12-16 18:19:44 +00:00
Hieu Hoang
df3f3d130f reuse-weights.perl --> substitute-weights.perl 2013-11-12 12:07:06 +00:00
Barry Haddow
97695164dd Basic support for WADE analysis
Partial support for running WADE (http://www.umiacs.umd.edu/~hal/damt/)
analysis from ems. You still need to create the input-reference alignments
somehow - for example by running training with the test set concatenated
to the training set.

To use WADE, (i) add 'wade = /path/to/wade.py' to the EVALUATION section and
(ii) add 'alignment = /path/to/alignments' to the approriate stanza
for each test set.
2013-11-01 16:56:55 +00:00
nadir
fb35e1f3c9 Training Scripts for Factored OSM 2013-08-26 13:21:04 +01:00
Hieu Hoang
02c7af3fb8 Mira changes. Manually applied Eva's patch 2013-08-12 13:03:26 +01:00
Nadir Durrani
d2bc6a2584 In EMS 2013-07-04 19:58:19 +01:00
Wilker Aziz
2c19238c24 Patching up the suffix array wrappers 2013-06-24 15:38:10 +01:00
phikoehn
542cd72c63 moved config creation back into train-model.perl 2013-05-19 03:28:02 +01:00
phikoehn
4cdffc8a89 fixes for sparse feature handling 2013-05-17 08:37:29 +01:00
Barry Haddow
585786d26b can specify location of create-ini 2013-05-16 19:34:56 +01:00
phikoehn
41da5b2760 Merge branch 'master' of git://github.com/moses-smt/mosesdecoder 2013-05-12 08:16:22 +01:00