search

dselivanov / text2vec

Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
http://text2vec.org
Other
850 stars 135 forks source link

GloVe vignette typo #250

Closed tvrbanec closed 6 years ago

tvrbanec commented 6 years ago

... the city you mentioned in web is correct or I just don't get it because of my english.

...if we take word vectors for the words “paris,” “france,” and “germany” and perform the following operation: vector("paris")−vector("france")+vector("germany") the resulting vector will be close to the vector for “rome.”

As I understand instead of rome it should be berlin.

dselivanov commented 6 years ago

Thanks for reporting. You are right. Will fix.