mosesdecoder/scripts/ems/example/config.syntax

################################################
### 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 binaries
moses-bin-dir = $moses-src-dir/bin
#
# moses scripts
moses-script-dir = $moses-src-dir/scripts
#
# directory where GIZA++/MGIZA programs resides
external-bin-dir = /Users/hieuhoang/workspace/bin/training-tools
#
# srilm
srilm-dir = $moses-src-dir/srilm/bin/i686
#
# irstlm
irstlm-dir = $moses-src-dir/irstlm/bin
#
# randlm
randlm-dir = $moses-src-dir/randlm/bin
#
# data
wmt12-data = $working-dir/data

### basic tools
#
# moses decoder
decoder = $moses-bin-dir/moses_chart

# conversion of phrase table into binary on-disk format
#ttable-binarizer = $moses-bin-dir/processPhraseTable

# conversion of rule table into binary on-disk format
ttable-binarizer = "$moses-bin-dir/CreateOnDiskPt 1 1 4 100 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

# syntactic parsers
collins = /home/pkoehn/bin/COLLINS-PARSER
output-parser = "$moses-script-dir/training/wrappers/parse-en-collins.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 = $wmt12-data/training/europarl-v7.$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 = $wmt12-data/training/news-commentary-v7.$pair-extension

[CORPUS:un] IGNORE
raw-stem = $wmt12-data/training/undoc.2000.$pair-extension

#################################################################
# LANGUAGE MODEL TRAINING

[LM]

### tool to be used for language model training
# kenlm training
lm-training = "$moses-script-dir/ems/support/lmplz-wrapper.perl -bin $moses-bin-dir/lmplz"
settings = "--prune '0 0 1' -T $working-dir/lm -S 20%"

# srilm 
#lm-training = $srilm-dir/ngram-count
#settings = "-interpolate -kndiscount -unk"

# irstlm training
# msb = modified kneser ney; p=0 no singleton pruning
#lm-training = "$moses-script-dir/generic/trainlm-irst2.perl -cores $cores -irst-dir $irstlm-dir -temp-dir $working-dir/tmp"
#settings = "-s msb -p 0"

# order of the language model
order = 5

### tool to be used for training randomized language model from scratch
# (more commonly, a SRILM is trained)
#
#rlm-training = "$randlm-dir/buildlm -falsepos 8 -values 8"

### script to use for binary table format for irstlm or kenlm
# (default: no binarization)

# irstlm
#lm-binarizer = $irstlm-dir/compile-lm

# kenlm, also set type to 8
lm-binarizer = $moses-bin-dir/build_binary
type = 8

### script to create quantized language model format (irstlm)
# (default: no quantization)
# 
#lm-quantizer = $irstlm-dir/quantize-lm

### script to use for converting into randomized table format
# (default: no randomization)
#
#lm-randomizer = "$randlm-dir/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 = $wmt12-data/training/europarl-v7.$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 = $wmt12-data/training/news-commentary-v7.$pair-extension.$output-extension

[LM:un] IGNORE
raw-corpus = $wmt12-data/training/undoc.2000.$pair-extension.$output-extension

[LM:news] IGNORE
raw-corpus = $wmt12-data/training/news.$output-extension.shuffled


#################################################################
# 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 = $wmt12-data/dev/newstest2010-ref.$output-extension.sgm
#raw-tuning =
#tokenized-tuning = 
#factored-tuning = 
#lowercased-tuning = 
#split-tuning = 

### group language models for hierarchical interpolation
# (flat interpolation is limited to 10 language models)
#group = "first,second fourth,fifth"

### script to use for binary table format for irstlm or kenlm
# (default: no binarization)

# irstlm
#lm-binarizer = $irstlm-dir/compile-lm

# kenlm, also set type to 8
lm-binarizer = $moses-bin-dir/build_binary
type = 8

### script to create quantized language model format (irstlm)
# (default: no quantization)
# 
#lm-quantizer = $irstlm-dir/quantize-lm

### script to use for converting into randomized table format
# (default: no randomization)
#
#lm-randomizer = "$randlm-dir/buildlm -falsepos 8 -values 8"

#################################################################
# MODIFIED MOORE LEWIS FILTERING

[MML] IGNORE

### specifications for language models to be trained
#
#lm-training = $srilm-dir/ngram-count
#lm-settings = "-interpolate -kndiscount -unk"
#lm-binarizer = $moses-src-dir/bin/build_binary
#lm-query = $moses-src-dir/bin/query
#order = 5

### in-/out-of-domain source/target corpora to train the 4 language model
# 
# in-domain: point either to a parallel corpus
#outdomain-stem = [CORPUS:toy:clean-split-stem]

# ... or to two separate monolingual corpora
#indomain-target = [LM:toy:lowercased-corpus]
#raw-indomain-source = $toy-data/nc-5k.$input-extension

# point to out-of-domain parallel corpus
#outdomain-stem = [CORPUS:giga:clean-split-stem]

# settings: number of lines sampled from the corpora to train each language model on
# (if used at all, should be small as a percentage of corpus)
#settings = "--line-count 100000"

#################################################################
# 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
# these are options that are passed on to train-model.perl, for instance
# * "-mgiza -mgiza-cpus 8" to use mgiza instead of giza
# * "-sort-buffer-size 8G -sort-compress gzip" to reduce on-disk sorting
# * "-sort-parallel 8 -cores 8" to speed up phrase table building
# * "-parallel" for parallel execution of mkcls and giza
#
#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 lemma pos morph
#output-factors = word lemma pos
#alignment-factors = "word -> word"
#translation-factors = "word -> word"
#reordering-factors = "word -> word"
#generation-factors = "word -> pos"
#decoding-steps = "t0, g0"

### parallelization of data preparation step
# the two directions of the data preparation can be run in parallel
# comment out if not needed
#
parallel = yes

### 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 Chris Dyer's fast align for word alignment
#
#fast-align-settings = "-d -o -v"

### 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

### use of baseline alignment model (incremental training)
# 
#baseline = 68
#baseline-alignment-model = "$working-dir/training/prepared.$baseline/$input-extension.vcb \
#  $working-dir/training/prepared.$baseline/$output-extension.vcb \
#  $working-dir/training/giza.$baseline/${output-extension}-$input-extension.cooc \
#  $working-dir/training/giza-inverse.$baseline/${input-extension}-$output-extension.cooc \ 
#  $working-dir/training/giza.$baseline/${output-extension}-$input-extension.thmm.5 \
#  $working-dir/training/giza.$baseline/${output-extension}-$input-extension.hhmm.5 \
#  $working-dir/training/giza-inverse.$baseline/${input-extension}-$output-extension.thmm.5 \
#  $working-dir/training/giza-inverse.$baseline/${input-extension}-$output-extension.hhmm.5"

### if word alignment should be skipped,
# point to word alignment files
#
#word-alignment = $working-dir/model/aligned.1

### filtering some corpora with modified Moore-Lewis
# specify corpora to be filtered and ratio to be kept, either before or after word alignment
#mml-filter-corpora = toy
#mml-before-wa = "-proportion 0.9"
#mml-after-wa = "-proportion 0.9"

### build memory mapped suffix array phrase table
# (binarizing the reordering table is a good idea, since filtering makes little sense)
#mmsapt = "num-features=9 pfwd=g+ pbwd=g+ smooth=0 sample=1000 workers=1"
#binarize-all = $moses-script-dir/training/binarize-model.perl

### create a bilingual concordancer for the model
#
#biconcor = $moses-bin-dir/biconcor

## Operation Sequence Model  (OSM)
# Durrani, Schmid and Fraser. (2011): 
# "A Joint Sequence Translation Model with Integrated Reordering"
# compile Moses with --max-kenlm-order=9 if higher order is required
# 
#operation-sequence-model = "yes"
#operation-sequence-model-order = 5
#operation-sequence-model-settings = "-lmplz '$moses-src-dir/bin/lmplz -S 40% -T $working-dir/model/tmp'"
#
# if OSM training should be skipped, point to OSM Model 
#osm-model =

### unsupervised transliteration module
# Durrani, Sajjad, Hoang and Koehn (EACL, 2014).
# "Integrating an Unsupervised Transliteration Model 
# into Statistical Machine Translation."
#
#transliteration-module = "yes"
#post-decoding-transliteration = "yes"

### 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 = "--MinHoleSource 1 --NonTermConsecSource"

### add extracted phrases from baseline model
#
#baseline-extract = $working-dir/model/extract.$baseline
#
# requires aligned parallel corpus for re-estimating lexical translation probabilities
#baseline-corpus = $working-dir/training/corpus.$baseline
#baseline-alignment = $working-dir/model/aligned.$baseline.$alignment-symmetrization-method

### 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 --MinScore 2:0.0001"

### include word alignment in phrase table
#
#include-word-alignment-in-rules = yes

### sparse lexical features
#
#sparse-features = "target-word-insertion top 50, source-word-deletion top 50, word-translation top 50 50, phrase-length"

### domain adaptation settings
# options: sparse, any of: indicator, subset, ratio
#domain-features = "subset" 

### 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 = 

### filtering the phrase table based on significance tests
# Johnson, Martin, Foster and Kuhn. (2007): "Improving Translation Quality by Discarding Most of the Phrasetable"
# options: -n number of translations; -l 'a+e', 'a-e', or a positive real value -log prob threshold
#salm-index = /path/to/project/salm/Bin/Linux/Index/IndexSA.O64
#sigtest-filter = "-l a+e -n 50"

### if training should be skipped, 
# point to a configuration file that contains
# pointers to all relevant model files
#
#config-with-reused-weights = 

#####################################################
### 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-bin-dir"

### specify the corpus used for tuning 
# it should contain 1000s of sentences
#
input-sgm = $wmt12-data/dev/newstest2010-src.$input-extension.sgm
#raw-input = 
#tokenized-input = 
#factorized-input = 
#input =
# 
reference-sgm = $wmt12-data/dev/newstest2010-ref.$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-bin-dir/moses

### 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
# common choices: 
#   "-threads N" for multi-threading
#   "-mbr" for MBR decoding
#   "-drop-unknown" for dropping unknown source words
#   "-search-algorithm 1 -cube-pruning-pop-limit 5000 -s 5000" for cube pruning
#
#decoder-settings = ""

### 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 = $moses-script-dir/generic/mteval-v13a.pl
nist-bleu-c = "$moses-script-dir/generic/mteval-v13a.pl -c"
#multi-bleu = "$moses-script-dir/generic/multi-bleu.perl -lc"
#multi-bleu-c = $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
# 
# visualization of the search graph in tree-based models
#analyze-search-graph = yes

[EVALUATION:newstest2011]

### input data
#
input-sgm = $wmt12-data/dev/newstest2011-src.$input-extension.sgm
# raw-input = 
# tokenized-input = 
# factorized-input =
# input = 

### reference data
#
reference-sgm = $wmt12-data/dev/newstest2011-ref.$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