dm.cs.tu-dortmund.de/mlbits/neural-nlp-architectures/
Basic Architectures for NLP – Lecture Notes
-Sequence [ SuViLe14 ] /2
Seq-2-Seq uses a straightforward application of LSTM, i.e., no changes in the basic architecture of LSTM cells. The main contributions are:
Use of 2 LSTMs for encoding/decoding [...] to sth.
\(\Downarrow\) embedding(stick) = [2.3, 5.4, 7.7]
\(\neq\)
The dog ran to get the stick .
\(=\) a thin piece of wood
\(\Downarrow\) embedding(stick) = [2.3, 5.4, 7.7]
Encoding each word into one [...] Modeling
Matrix Factorization
Sequential Models
Neural Text Embeddings
Early Embeddings – Word2Vec
Beyond Word2Vec
Neural Networks Fundamentals
Basic Architectures for NLP
Transformer Architecture
Attention …