echo "Building the lexicon ..."
#echo "Removing line feed from corpus..."
tr '\015' ' ' < $1 > corpus.tmp
echo "Sorting (word,tag) pairs by frequency ..." 
sort corpus.tmp | uniq -c | sort -nr > $1.freq 
echo "Grouping words and associated tags ..." 
perl buildDictTagFreq.pl $1.freq $2
rm *.tmp
