mirror of
https://github.com/moses-smt/mosesdecoder.git
synced 2024-09-20 07:42:21 +03:00
a1ca2722df
prunes non-initial rules (i.e. rules with non-terminals) from the rule table based on their frequency counts. In Zollmann, Venugopal, Och, and Ponte (2008), pruning hierarchical rules that occur only once was found to significantly decrease rule table size without harming translation quality. Also, add TUNING:filter-settings and EVALUATION[:<set>]:filter-settings variables so that this can be enabled in the EMS. git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@4033 1f5c12ca-751b-0410-a591-d2e778427230
555 lines
14 KiB
Plaintext
555 lines
14 KiB
Plaintext
################################################
|
|
### CONFIGURATION FILE FOR AN SMT EXPERIMENT ###
|
|
################################################
|
|
|
|
[GENERAL]
|
|
|
|
### directory in which experiment is run
|
|
#
|
|
working-dir = /home/pkoehn/experiment
|
|
|
|
# specification of the language pair
|
|
input-extension = fr
|
|
output-extension = en
|
|
pair-extension = fr-en
|
|
|
|
### directories that contain tools and data
|
|
#
|
|
# moses
|
|
moses-src-dir = /home/pkoehn/moses
|
|
#
|
|
# moses scripts
|
|
moses-script-dir = /home/pkoehn/moses/scripts
|
|
#
|
|
# srilm
|
|
srilm-dir = $moses-src-dir/srilm/bin/i686
|
|
#
|
|
# data
|
|
wmt10-data = $working-dir/data
|
|
|
|
### basic tools
|
|
#
|
|
# moses decoder
|
|
decoder = $moses-src-dir/moses-cmd/src/moses
|
|
|
|
# conversion of phrase table into binary on-disk format
|
|
ttable-binarizer = $moses-src-dir/misc/processPhraseTable
|
|
|
|
# conversion of rule table into binary on-disk format
|
|
#ttable-binarizer = "$moses-src-dir/CreateOnDisk/src/CreateOnDiskPt 1 1 5 100 2"
|
|
|
|
# tokenizers - comment out if all your data is already tokenized
|
|
input-tokenizer = "$moses-script-dir/tokenizer/tokenizer.perl -a -l $input-extension"
|
|
output-tokenizer = "$moses-script-dir/tokenizer/tokenizer.perl -a -l $output-extension"
|
|
|
|
# truecasers - comment out if you do not use the truecaser
|
|
input-truecaser = $moses-script-dir/recaser/truecase.perl
|
|
output-truecaser = $moses-script-dir/recaser/truecase.perl
|
|
detruecaser = $moses-script-dir/recaser/detruecase.perl
|
|
|
|
### generic parallelizer for cluster and multi-core machines
|
|
# you may specify a script that allows the parallel execution
|
|
# parallizable steps (see meta file). you also need specify
|
|
# the number of jobs (cluster) or cores (multicore)
|
|
#
|
|
#generic-parallelizer = $moses-script-dir/ems/support/generic-parallelizer.perl
|
|
#generic-parallelizer = $moses-script-dir/ems/support/generic-multicore-parallelizer.perl
|
|
|
|
### cluster settings (if run on a cluster machine)
|
|
# number of jobs to be submitted in parallel
|
|
#
|
|
#jobs = 10
|
|
|
|
# arguments to qsub when scheduling a job
|
|
#qsub-settings = ""
|
|
|
|
# project for priviledges and usage accounting
|
|
#qsub-project = iccs_smt
|
|
|
|
# memory and time
|
|
#qsub-memory = 4
|
|
#qsub-hours = 48
|
|
|
|
### multi-core settings
|
|
# when the generic parallelizer is used, the number of cores
|
|
# specified here
|
|
cores = 8
|
|
|
|
#################################################################
|
|
# PARALLEL CORPUS PREPARATION:
|
|
# create a tokenized, sentence-aligned corpus, ready for training
|
|
|
|
[CORPUS]
|
|
|
|
### long sentences are filtered out, since they slow down GIZA++
|
|
# and are a less reliable source of data. set here the maximum
|
|
# length of a sentence
|
|
#
|
|
max-sentence-length = 80
|
|
|
|
[CORPUS:europarl] IGNORE
|
|
|
|
### command to run to get raw corpus files
|
|
#
|
|
# get-corpus-script =
|
|
|
|
### raw corpus files (untokenized, but sentence aligned)
|
|
#
|
|
raw-stem = $wmt10-data/training/europarl-v5.$pair-extension
|
|
|
|
### tokenized corpus files (may contain long sentences)
|
|
#
|
|
#tokenized-stem =
|
|
|
|
### if sentence filtering should be skipped,
|
|
# point to the clean training data
|
|
#
|
|
#clean-stem =
|
|
|
|
### if corpus preparation should be skipped,
|
|
# point to the prepared training data
|
|
#
|
|
#lowercased-stem =
|
|
|
|
[CORPUS:nc]
|
|
raw-stem = $wmt10-data/training/news-commentary10.$pair-extension
|
|
|
|
[CORPUS:un] IGNORE
|
|
raw-stem = $wmt10-data/training/undoc.2000.$pair-extension
|
|
|
|
#################################################################
|
|
# LANGUAGE MODEL TRAINING
|
|
|
|
[LM]
|
|
|
|
### tool to be used for language model training
|
|
# for instance: ngram-count (SRILM), train-lm-on-disk.perl (Edinburgh)
|
|
#
|
|
lm-training = $srilm-dir/ngram-count
|
|
settings = "-interpolate -kndiscount -unk"
|
|
order = 5
|
|
|
|
### tool to be used for training randomized language model from scratch
|
|
# (more commonly, a SRILM is trained)
|
|
#
|
|
#rlm-training = "$moses-src-dir/randlm/bin/buildlm -falsepos 8 -values 8"
|
|
|
|
### script to use for binary table format for irstlm or kenlm
|
|
# (default: no binarization)
|
|
|
|
# irstlm
|
|
#lm-binarizer = $moses-src-dir/irstlm/bin/compile-lm
|
|
|
|
# kenlm, also set type to 8
|
|
#lm-binarizer = $moses-src-dir/kenlm/build_binary
|
|
#type = 8
|
|
|
|
### script to create quantized language model format (irstlm)
|
|
# (default: no quantization)
|
|
#
|
|
#lm-quantizer = $moses-src-dir/irstlm/bin/quantize-lm
|
|
|
|
### script to use for converting into randomized table format
|
|
# (default: no randomization)
|
|
#
|
|
#lm-randomizer = "$moses-src-dir/randlm/bin/buildlm -falsepos 8 -values 8"
|
|
|
|
### each language model to be used has its own section here
|
|
|
|
[LM:europarl] IGNORE
|
|
|
|
### command to run to get raw corpus files
|
|
#
|
|
#get-corpus-script = ""
|
|
|
|
### raw corpus (untokenized)
|
|
#
|
|
raw-corpus = $wmt10-data/training/europarl-v5.$output-extension
|
|
|
|
### tokenized corpus files (may contain long sentences)
|
|
#
|
|
#tokenized-corpus =
|
|
|
|
### if corpus preparation should be skipped,
|
|
# point to the prepared language model
|
|
#
|
|
#lm =
|
|
|
|
[LM:nc]
|
|
raw-corpus = $wmt10-data/training/news-commentary10.$pair-extension.$output-extension
|
|
|
|
[LM:un] IGNORE
|
|
raw-corpus = $wmt10-data/training/undoc.2000.$pair-extension.$output-extension
|
|
|
|
[LM:news] IGNORE
|
|
raw-corpus = $wmt10-data/training/news.$output-extension.shuffled
|
|
|
|
[LM:nc=pos]
|
|
factors = "pos"
|
|
order = 7
|
|
settings = "-interpolate -unk"
|
|
raw-corpus = $wmt10-data/training/news-commentary10.$pair-extension.$output-extension
|
|
|
|
#################################################################
|
|
# INTERPOLATING LANGUAGE MODELS
|
|
|
|
[INTERPOLATED-LM] IGNORE
|
|
|
|
# if multiple language models are used, these may be combined
|
|
# by optimizing perplexity on a tuning set
|
|
# see, for instance [Koehn and Schwenk, IJCNLP 2008]
|
|
|
|
### script to interpolate language models
|
|
# if commented out, no interpolation is performed
|
|
#
|
|
script = $moses-script-dir/ems/support/interpolate-lm.perl
|
|
|
|
### tuning set
|
|
# you may use the same set that is used for mert tuning (reference set)
|
|
#
|
|
tuning-sgm = $wmt10-data/dev/news-test2008-ref.$output-extension.sgm
|
|
#raw-tuning =
|
|
#tokenized-tuning =
|
|
#factored-tuning =
|
|
#lowercased-tuning =
|
|
#split-tuning =
|
|
|
|
### script to use for binary table format for irstlm or kenlm
|
|
# (default: no binarization)
|
|
|
|
# irstlm
|
|
#lm-binarizer = $moses-src-dir/irstlm/bin/compile-lm
|
|
|
|
# kenlm, also set type to 8
|
|
#lm-binarizer = $moses-src-dir/kenlm/build_binary
|
|
#type = 8
|
|
|
|
### script to create quantized language model format (irstlm)
|
|
# (default: no quantization)
|
|
#
|
|
#lm-quantizer = $moses-src-dir/irstlm/bin/quantize-lm
|
|
|
|
### script to use for converting into randomized table format
|
|
# (default: no randomization)
|
|
#
|
|
#lm-randomizer = "$moses-src-dir/randlm/bin/buildlm -falsepos 8 -values 8"
|
|
|
|
#################################################################
|
|
# FACTOR DEFINITION
|
|
|
|
[INPUT-FACTOR]
|
|
|
|
# also used for output factors
|
|
temp-dir = $working-dir/training/factor
|
|
|
|
[OUTPUT-FACTOR:pos]
|
|
|
|
### script that generates this factor
|
|
#
|
|
mxpost = /home/pkoehn/bin/mxpost
|
|
factor-script = "$moses-script-dir/training/wrappers/make-factor-en-pos.mxpost.perl -mxpost $mxpost"
|
|
|
|
#################################################################
|
|
# TRANSLATION MODEL TRAINING
|
|
|
|
[TRAINING]
|
|
|
|
### training script to be used: either a legacy script or
|
|
# current moses training script (default)
|
|
#
|
|
script = $moses-script-dir/training/train-model.perl
|
|
|
|
### general options
|
|
#
|
|
#training-options = ""
|
|
|
|
### factored training: specify here which factors used
|
|
# if none specified, single factor training is assumed
|
|
# (one translation step, surface to surface)
|
|
#
|
|
input-factors = word
|
|
output-factors = word pos
|
|
alignment-factors = "word -> word"
|
|
translation-factors = "word -> word+pos"
|
|
reordering-factors = "word -> word"
|
|
#generation-factors =
|
|
decoding-steps = "t0"
|
|
|
|
### pre-computation for giza++
|
|
# giza++ has a more efficient data structure that needs to be
|
|
# initialized with snt2cooc. if run in parallel, this may reduces
|
|
# memory requirements. set here the number of parts
|
|
#
|
|
run-giza-in-parts = 5
|
|
|
|
### symmetrization method to obtain word alignments from giza output
|
|
# (commonly used: grow-diag-final-and)
|
|
#
|
|
alignment-symmetrization-method = grow-diag-final-and
|
|
|
|
### use of berkeley aligner for word alignment
|
|
#
|
|
#use-berkeley = true
|
|
#alignment-symmetrization-method = berkeley
|
|
#berkeley-train = $moses-script-dir/ems/support/berkeley-train.sh
|
|
#berkeley-process = $moses-script-dir/ems/support/berkeley-process.sh
|
|
#berkeley-jar = /your/path/to/berkeleyaligner-1.1/berkeleyaligner.jar
|
|
#berkeley-java-options = "-server -mx30000m -ea"
|
|
#berkeley-training-options = "-Main.iters 5 5 -EMWordAligner.numThreads 8"
|
|
#berkeley-process-options = "-EMWordAligner.numThreads 8"
|
|
#berkeley-posterior = 0.5
|
|
|
|
### if word alignment should be skipped,
|
|
# point to word alignment files
|
|
#
|
|
#word-alignment = $working-dir/model/aligned.1
|
|
|
|
### create a bilingual concordancer for the model
|
|
#
|
|
#biconcor = $moses-script-dir/ems/biconcor/biconcor
|
|
|
|
### lexicalized reordering: specify orientation type
|
|
# (default: only distance-based reordering model)
|
|
#
|
|
lexicalized-reordering = msd-bidirectional-fe
|
|
|
|
### hierarchical rule set
|
|
#
|
|
#hierarchical-rule-set = true
|
|
|
|
### settings for rule extraction
|
|
#
|
|
#extract-settings = ""
|
|
|
|
### unknown word labels (target syntax only)
|
|
# enables use of unknown word labels during decoding
|
|
# label file is generated during rule extraction
|
|
#
|
|
#use-unknown-word-labels = true
|
|
|
|
### if phrase extraction should be skipped,
|
|
# point to stem for extract files
|
|
#
|
|
# extracted-phrases =
|
|
|
|
### settings for rule scoring
|
|
#
|
|
score-settings = "--GoodTuring"
|
|
|
|
### include word alignment in phrase table
|
|
#
|
|
#include-word-alignment-in-rules = yes
|
|
|
|
### if phrase table training should be skipped,
|
|
# point to phrase translation table
|
|
#
|
|
# phrase-translation-table =
|
|
|
|
### if reordering table training should be skipped,
|
|
# point to reordering table
|
|
#
|
|
# reordering-table =
|
|
|
|
### if training should be skipped,
|
|
# point to a configuration file that contains
|
|
# pointers to all relevant model files
|
|
#
|
|
#config =
|
|
|
|
#####################################################
|
|
### TUNING: finding good weights for model components
|
|
|
|
[TUNING]
|
|
|
|
### instead of tuning with this setting, old weights may be recycled
|
|
# specify here an old configuration file with matching weights
|
|
#
|
|
#weight-config = $working-dir/tuning/moses.weight-reused.ini.1
|
|
|
|
### tuning script to be used
|
|
#
|
|
tuning-script = $moses-script-dir/training/mert-moses.pl
|
|
tuning-settings = "-mertdir $moses-src-dir/mert"
|
|
|
|
### specify the corpus used for tuning
|
|
# it should contain 1000s of sentences
|
|
#
|
|
input-sgm = $wmt10-data/dev/news-test2008-src.$input-extension.sgm
|
|
#raw-input =
|
|
#tokenized-input =
|
|
#factorized-input =
|
|
#input =
|
|
#
|
|
reference-sgm = $wmt10-data/dev/news-test2008-ref.$output-extension.sgm
|
|
#raw-reference =
|
|
#tokenized-reference =
|
|
#factorized-reference =
|
|
#reference =
|
|
|
|
### size of n-best list used (typically 100)
|
|
#
|
|
nbest = 100
|
|
|
|
### ranges for weights for random initialization
|
|
# if not specified, the tuning script will use generic ranges
|
|
# it is not clear, if this matters
|
|
#
|
|
# lambda =
|
|
|
|
### additional flags for the filter script
|
|
#
|
|
filter-settings = ""
|
|
|
|
### additional flags for the decoder
|
|
#
|
|
decoder-settings = ""
|
|
|
|
### if tuning should be skipped, specify this here
|
|
# and also point to a configuration file that contains
|
|
# pointers to all relevant model files
|
|
#
|
|
#config =
|
|
|
|
#########################################################
|
|
## RECASER: restore case, this part only trains the model
|
|
|
|
[RECASING]
|
|
|
|
#decoder = $moses-src-dir/moses-cmd/src/moses.1521.srilm
|
|
|
|
### training data
|
|
# raw input needs to be still tokenized,
|
|
# also also tokenized input may be specified
|
|
#
|
|
#tokenized = [LM:europarl:tokenized-corpus]
|
|
|
|
# recase-config =
|
|
|
|
#lm-training = $srilm-dir/ngram-count
|
|
|
|
#######################################################
|
|
## TRUECASER: train model to truecase corpora and input
|
|
|
|
[TRUECASER]
|
|
|
|
### script to train truecaser models
|
|
#
|
|
trainer = $moses-script-dir/recaser/train-truecaser.perl
|
|
|
|
### training data
|
|
# data on which truecaser is trained
|
|
# if no training data is specified, parallel corpus is used
|
|
#
|
|
# raw-stem =
|
|
# tokenized-stem =
|
|
|
|
### trained model
|
|
#
|
|
# truecase-model =
|
|
|
|
######################################################################
|
|
## EVALUATION: translating a test set using the tuned system and score it
|
|
|
|
[EVALUATION]
|
|
|
|
### number of jobs (if parallel execution on cluster)
|
|
#
|
|
#jobs = 10
|
|
|
|
### additional flags for the filter script
|
|
#
|
|
#filter-settings = ""
|
|
|
|
### additional decoder settings
|
|
# switches for the Moses decoder
|
|
#
|
|
decoder-settings = "-search-algorithm 1 -cube-pruning-pop-limit 5000 -s 5000"
|
|
|
|
### specify size of n-best list, if produced
|
|
#
|
|
#nbest = 100
|
|
|
|
### multiple reference translations
|
|
#
|
|
#multiref = yes
|
|
|
|
### prepare system output for scoring
|
|
# this may include detokenization and wrapping output in sgm
|
|
# (needed for nist-bleu, ter, meteor)
|
|
#
|
|
detokenizer = "$moses-script-dir/tokenizer/detokenizer.perl -l $output-extension"
|
|
#recaser = $moses-script-dir/recaser/recase.perl
|
|
wrapping-script = "$moses-script-dir/ems/support/wrap-xml.perl $output-extension"
|
|
#output-sgm =
|
|
|
|
### BLEU
|
|
#
|
|
nist-bleu = $moses-script-dir/generic/mteval-v12.pl
|
|
nist-bleu-c = "$moses-script-dir/generic/mteval-v12.pl -c"
|
|
#multi-bleu = $moses-script-dir/generic/multi-bleu.perl
|
|
#ibm-bleu =
|
|
|
|
### TER: translation error rate (BBN metric) based on edit distance
|
|
# not yet integrated
|
|
#
|
|
# ter =
|
|
|
|
### METEOR: gives credit to stem / worknet synonym matches
|
|
# not yet integrated
|
|
#
|
|
# meteor =
|
|
|
|
### Analysis: carry out various forms of analysis on the output
|
|
#
|
|
analysis = $moses-script-dir/ems/support/analysis.perl
|
|
#
|
|
# also report on input coverage
|
|
analyze-coverage = yes
|
|
#
|
|
# also report on phrase mappings used
|
|
report-segmentation = yes
|
|
#
|
|
# report precision of translations for each input word, broken down by
|
|
# count of input word in corpus and model
|
|
#report-precision-by-coverage = yes
|
|
#
|
|
# further precision breakdown by factor
|
|
#precision-by-coverage-factor = pos
|
|
|
|
[EVALUATION:newstest2009]
|
|
|
|
### input data
|
|
#
|
|
input-sgm = $wmt10-data/dev/newstest2009-src.$input-extension.sgm
|
|
# raw-input =
|
|
# tokenized-input =
|
|
# factorized-input =
|
|
# input =
|
|
|
|
### reference data
|
|
#
|
|
reference-sgm = $wmt10-data/dev/newstest2009-ref.$output-extension.sgm
|
|
# raw-reference =
|
|
# tokenized-reference =
|
|
# reference =
|
|
|
|
### analysis settings
|
|
# may contain any of the general evaluation analysis settings
|
|
# specific setting: base coverage statistics on earlier run
|
|
#
|
|
#precision-by-coverage-base = $working-dir/evaluation/test.analysis.5
|
|
|
|
### wrapping frame
|
|
# for nist-bleu and other scoring scripts, the output needs to be wrapped
|
|
# in sgm markup (typically like the input sgm)
|
|
#
|
|
wrapping-frame = $input-sgm
|
|
|
|
##########################################
|
|
### REPORTING: summarize evaluation scores
|
|
|
|
[REPORTING]
|
|
|
|
### currently no parameters for reporting section
|
|
|