自然语言处理——Seq2Seq_01
1.Padding:
First, we need to convert the variable length into fixed length sequence by padding.
Take the following query-response as the example.
Q: How are you?
A: I'm fine.
After the padding, it becomes:
2.Bucketing:
I don't want the length to be fixed, so, I consider the list of [ (5,10), (10,15), (20,25), (40,50) ].
take the same sentence as the example, it becomes :
3. word embedding:
In the Seq2Seq model, the weights of the embedding layer are jointly trained with other parameters of the model.
4. Attention Mechanism (I think this is very distinguished and very useful)