Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings
6.86k
stars
1.51k
forks
source link
Fixed misleading README.md about inserting "dummy" words between documents in corpus #110
Closed
jbojar closed 6 years ago
GloVe supports documents separated by new line characters (\n) in corpus. Inserting multiple "dummy" words to separate documents is not necessary.
Detecting line feeds (\n) is done in function
get_word
in cooccur.c.