dselivanov / text2vec

Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
http://text2vec.org
Other
851 stars 136 forks source link

Small writing mistake on website #282

Closed lhk closed 4 years ago

lhk commented 6 years ago

Here, under Linguistic regularities, you are demonstrating how the embedding allows simple arithmetic operations:

vector("paris")−vector("france")+vector("germany") the resulting vector will be close to the vector for “rome.”

It would be more impressive if the resulting vector was close to "berlin" ;) (I assume it does give you berlin ?)