2013-08-01 01:00:52 +02:00
|
|
|
make
|
|
|
|
|
if [ ! -e text8 ]; then
|
|
|
|
|
wget http://mattmahoney.net/dc/text8.zip -O text8.gz
|
|
|
|
|
gzip -d text8.gz -f
|
|
|
|
|
fi
|
|
|
|
|
echo -----------------------------------------------------------------------------------------------------
|
|
|
|
|
echo Note that for the word analogy to perform well, the models should be trained on much larger data sets
|
|
|
|
|
echo Example input: paris france berlin
|
|
|
|
|
echo -----------------------------------------------------------------------------------------------------
|
2013-08-01 21:28:23 +02:00
|
|
|
time ./word2vec -train text8 -output vectors.bin -cbow 0 -size 200 -window 5 -negative 0 -hs 1 -sample 1e-3 -threads 12 -binary 1
|
2013-08-01 01:00:52 +02:00
|
|
|
./word-analogy vectors.bin
|
