sub x{
my( @a, @b ) = @_;
print "a:[@a]\nb:[@b]";
};
@x = 1..10;
@y = 'a'..'f';;
print "x:[@x]\ny:[@y]";;
x:[1 2 3 4 5 6 7 8 9 10]
y:[a b c d e f]
x( @x, @y );;
a:[1 2 3 4 5 6 7 8 9 10 a b c d e f]
b:[]
####
sub MI {
my( $string_es, $string_en, $hash_es, $hash_en ) = @_;
my $prob_es = ( keys %$hash_es ) / 6939873;
my $prob_en = ( keys %$hash_en ) / 6939873;
my $common = 0;
exists $hash_en->{ $_ } and ++$common for keys %$hash_es;
my $prob_es_en= ( $common ) / 6939873;
$prob_es_en = ( $prob_es_en + ( $prob_es * $prob_en * 0.1) ) / 1.1;
my $mi = $prob_es_en * log( $prob_es_en / ( $prob_es * $prob_en ) );
return $mi;
}
##
##
#create hash files from ngram statistics
my %hash_en;
to_hash( \%hash_en, $file_in_en );
my %hash_es;
to_hash( \%hash_es, $file_in_es );
...
sub to_hash {
my( $href, $file ) = @_;
open(FILE, "<$file");
foreach my $l () {
my( $ngram, $line ) = split /\t/, $l;
push @{ $href->{ $ngram } }, $line;
}
close FILE;
}