New answers tagged gensim
3
One way to test your embedding is see how often your model agrees with the common consensus of how other embeddings complete word analogies. A collection of established word embedding analogies are here.
6
The reason to average the embedded vectors of the words in a paragraph or document is to obtain a single fixed-size vector that represents the whole text. Then, the document-level vector can be used as input to a document classification model or any other document-level model.
If you explicitly want to compute word-level representations and then combine them ...
Top 50 recent answers are included
Related Tags
gensim × 84word2vec × 46
nlp × 35
python × 26
word-embeddings × 24
machine-learning × 12
lda × 12
topic-model × 10
text-mining × 7
similar-documents × 6
cosine-distance × 5
scikit-learn × 4
data-mining × 4
classification × 3
lsi × 3
neural-network × 2
keras × 2
natural-language-process × 2
similarity × 2
embeddings × 2
deep-learning × 1
tensorflow × 1
cnn × 1
clustering × 1
predictive-modeling × 1