forked from facebookarchive/MIXER
-
Notifications
You must be signed in to change notification settings - Fork 0
/
prepareData.sh
95 lines (78 loc) · 2.39 KB
/
prepareData.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
#!/usr/bin/env bash
echo 'Cloning Moses github repository (for tokenization scripts)...'
git clone https://github.com/moses-smt/mosesdecoder.git
SCRIPTS=mosesdecoder/scripts
TOKENIZER=$SCRIPTS/tokenizer/tokenizer.perl
LC=$SCRIPTS/tokenizer/lowercase.perl
CLEAN=$SCRIPTS/training/clean-corpus-n.perl
URL="http://wit3.fbk.eu/archive/2014-01/texts/de/en/de-en.tgz"
GZ=de-en.tgz
if [ ! -d "$SCRIPTS" ]; then
echo "Please set SCRIPTS variable correctly to point to Moses scripts."
exit
fi
src=de
tgt=en
lang=de-en
prep=prep
tmp=prep/tmp
orig=orig
mkdir -p $orig $tmp $prep
echo "Downloading data from ${URL}..."
cd $orig
http_proxy=fwdproxy:8080 https_proxy=fwdproxy:8080 wget "$URL"
if [ -f $GZ ]; then
echo "Data successfully downloaded."
else
echo "Data not successfully downloaded."
exit
fi
tar zxvf $GZ
cd ..
echo "pre-processing train data..."
for l in $src $tgt; do
f=train.tags.$lang.$l
tok=train.tags.$lang.tok.$l
cat $orig/$lang/$f | \
grep -v '<url>' | \
grep -v '<talkid>' | \
grep -v '<keywords>' | \
sed -e 's/<title>//g' | \
sed -e 's/<\/title>//g' | \
sed -e 's/<description>//g' | \
sed -e 's/<\/description>//g' | \
perl $TOKENIZER -threads 8 -l $l > $tmp/$tok
echo ""
done
perl $CLEAN -ratio 1.5 $tmp/train.tags.$lang.tok $src $tgt $tmp/train.tags.$lang.clean 1 50
for l in $src $tgt; do
perl $LC < $tmp/train.tags.$lang.clean.$l > $tmp/train.tags.$lang.$l
done
echo "pre-processing valid/test data..."
for l in $src $tgt; do
for o in `ls $orig/$lang/IWSLT14.TED*.$l.xml`; do
fname=${o##*/}
f=$tmp/${fname%.*}
echo $o $f
grep '<seg id' $o | \
sed -e 's/<seg id="[0-9]*">\s*//g' | \
sed -e 's/\s*<\/seg>\s*//g' | \
sed -e "s/\’/\'/g" | \
perl $TOKENIZER -threads 8 -l $l | \
perl $LC > $f
echo ""
done
done
echo "creating train, valid, test..."
for l in $src $tgt; do
awk '{if (NR%23 == 0) print $0; }' $tmp/train.tags.de-en.$l > $prep/valid.de-en.$l
awk '{if (NR%23 != 0) print $0; }' $tmp/train.tags.de-en.$l > $prep/train.de-en.$l
cat $tmp/IWSLT14.TED.dev2010.de-en.$l \
$tmp/IWSLT14.TEDX.dev2012.de-en.$l \
$tmp/IWSLT14.TED.tst2010.de-en.$l \
$tmp/IWSLT14.TED.tst2011.de-en.$l \
$tmp/IWSLT14.TED.tst2012.de-en.$l \
> $prep/test.de-en.$l
done
echo "binarizing train, valid, test..."
th makedata.lua -dstDir data -srcDir prep