TAU2019-028/preprocess-train/preprocess-data.sh

63 lines
2.5 KiB
Bash
Executable File

#!/bin/bash -v
# This sample script preprocesses a sample corpus, including tokenization,
# truecasing, and subword segmentation.
# For application to a different language pair, change source and target
# prefix, optionally the number of BPE operations, and the file names
# (currently, data/corpus and data/newsdev2016 are being processed).
# In the tokenization step, you will want to remove Romanian-specific
# normalization / diacritic removal, and you may want to add your own.
# Also, you may want to learn BPE segmentations separately for each language,
# especially if they differ in their alphabet
# Suffix of source language files
SRC=cs
# Suffix of target language files
TRG=en
# Number of merge operations. Network vocabulary should be slightly larger (to
# include characters), or smaller if the operations are learned on the joint
# vocabulary
bpe_operations=85000
# path to moses decoder: https://github.com/moses-smt/mosesdecoder
mosesdecoder=/home/jakub/TAU/TAU_24/marian-dev/examples/tools/moses-scripts
# path to subword segmentation scripts: https://github.com/rsennrich/subword-nmt
subword_nmt=/home/jakub/TAU/TAU_24/marian-dev/examples/tools/subword-nmt
# tokenize
for prefix in europarl valideuroparl
do
cat data/$prefix.$SRC \
| $mosesdecoder/scripts/tokenizer/tokenizer.perl -a -l $SRC > data/$prefix.tok.$SRC
cat data/$prefix.$TRG \
| $mosesdecoder/scripts/tokenizer/tokenizer.perl -a -l $TRG > data/$prefix.tok.$TRG
done
# clean empty and long sentences, and sentences with high source-target ratio (training corpus only)
$mosesdecoder/scripts/training/clean-corpus-n.perl data/europarl.tok $SRC $TRG data/europarl.tok.clean 1 80
# train truecaser
$mosesdecoder/scripts/recaser/train-truecaser.perl -corpus data/europarl.tok.clean.$SRC -model model/tc.$SRC
$mosesdecoder/scripts/recaser/train-truecaser.perl -corpus data/europarl.tok.clean.$TRG -model model/tc.$TRG
# apply truecaser (cleaned training corpus)
for prefix in europarl
do
$mosesdecoder/scripts/recaser/truecase.perl -model model/tc.$SRC < data/$prefix.tok.clean.$SRC > data/$prefix.tc.$SRC
$mosesdecoder/scripts/recaser/truecase.perl -model model/tc.$TRG < data/$prefix.tok.clean.$TRG > data/$prefix.tc.$TRG
done
# apply truecaser (dev/test files)
for prefix in valideuroparl
do
$mosesdecoder/scripts/recaser/truecase.perl -model model/tc.$SRC < data/$prefix.tok.$SRC > data/$prefix.tc.$SRC
$mosesdecoder/scripts/recaser/truecase.perl -model model/tc.$TRG < data/$prefix.tok.$TRG > data/$prefix.tc.$TRG
done