Understanding Seq2Seq Neural Networks – Part 5: Decoding the Context Vector

In the previous article, we stopped at the concept of the context vector. In this article, we will start by decoding the context vector. Connecting the Decoder The first thing we need to do is connect the long-term and short-term memories (the cell states and hidden states) that form the context vector to a new set of LSTMs. Just like the encoder, the decoder will also have two layers, and each layer will have two LSTM cells. The LSTMs in the decoder are different from the ones in the encoder and have their own separate weights and biases. Using the Context Vector The context vector is used to initialize the long-term and short-term memories (the cell states and hidden states) in the LSTMs of the decoder. This is important because it allows the decoder to start with the information learned from the input sentence. Goal of the Decoder The ultimate goal of the decoder is to convert the context vector into the output sentence. In simple terms, the encoder understands the input, and the de