All Questions
Tagged with n-gram natural-language-processing
1 question with no upvoted or accepted answers
0
votes
1
answer
161
views
Why would adding all the possible embeddings be "worse" than using 1D-convolutions?
Suppose we are using word2vec and have embeddings of individual words $w_1, \dots, w_{10}$. Let's say we wanted to analyze $2$ grams or $3$ grams.
Why would adding all the possible embeddings, $\binom{...
- 51