New answers tagged word2vec
0
votes
Why use the cosine distance for machine translation (Mikolov paper)?
A hypothesis on why the cosine similarity loss could be more efficient for training neural networks on parallel sentences comprised of Word2Vec vectors:
The ...
Top 50 recent answers are included
Related Tags
word2vec × 204word-embeddings × 112
natural-language × 94
neural-networks × 64
machine-learning × 58
classification × 11
python × 10
text-mining × 10
tensorflow × 9
doc2vec × 8
embeddings × 7
self-study × 6
cosine-similarity × 6
bag-of-words × 6
keras × 5
softmax × 5
latent-dirichlet-alloc × 5
lstm × 4
similarities × 4
clustering × 3
dimensionality-reduction × 3
gradient-descent × 3
feature-engineering × 3
topic-models × 3
tsne × 3