Deep n-grams (in Course 3: Natural Language Processing with Sequence Models week 4) vs Word Embedding (built by CBOWs in Course 2 Natural Language Processing with Probabilistic Models week 4))

[arvyzukai]

Hi @Hung_Nguyen1

@Hung_Nguyen1

However, the pros and cons of deep(GRU, LSTM) n-grams against word embeddings were not discussed.

I think you misunderstand what are the word embeddings because it’s not about “deep(GRU, LSTM) n-grams against word embeddings”.

Here are some threads about word embeddings:

• Intuition behind using the weights of a CBOW model as word embeddings
• How does trax word embedding layer work?
• Embedding layer, why is it needed?

And also some threads about RNNs:

• LSTM and encoder_layers
• RNN simple calculations’ example

Cheers