Questions tagged [n-gram]

For questions about the concept of an n-gram in the context of natural language processing and other AI sub-fields.

Filter by
Sorted by
Tagged with
0
votes
1answer
89 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{...