|
|
|
|
|
|
by seanthemon
1040 days ago
|
|
|
Many ways to skin this question, but in essence a simple idea is that word vectorization is assigning a numerical representation to a specific word, embeddings on the other hand are taking those words, turning them into numerical representations but keeping semantically similar words closer dimensionally. Yes, turning words into vectors is it's own class of machine learning. You can learn a lot on the NLP course on hugging face https://huggingface.co/learn/nlp-course/chapter1/1 (and on youtube). |
|
|