Translation from English to French using encoder-decoder model.
We have 10,000 english sentences and corresponding 10,000 translated French sentences. Approach for training is as follows :
- Create one-hot character embeddings for English and French sentences. These will be the inputs to the encoder and the decoder. The French one-hot character embeds will also be used as target data for loss function.
- Feed character by character embeds into the encoder till the end of the English sentence sequence.
- Obtain the final encoder states (hidden and cell states) and feed them into the decoder as its initial state.
- Decoder will have 3 inputs at every time step — 2 decoder states and the French character embeds fed to it character by character.
- At every step of the decoder, the output of the decoder is sent to softmax layer that is compared with the target data.
Prediction
There are major changes in the decoder network.
- Encoder Side of network remains same as before.
- At the first time step, the decoder has 3 inputs — the start tag ‘\t’ and the two encoder states. We input the first character as ‘\t’ ( its one hot embed vector) into the first time step of the decoder.
- From next time step on wards the decoder still has 3 inputs but different from the first time step . They being — one hot encode of previous predicted character, previous decoder cell state and the previous decoder hidden state
Training Model
Prediction Model
