An alternative approach to training Sequence-to-Sequence model for Machine Translation
Vivek Sah · Digital Commons - Colby (Colby College) · 2017
Machine translation is a widely researched topic in the field of Natural Language Processing and most recently, neural network models have been shown to be very effective at this task. The model, called sequence-to-sequence model, learns to map an input sequence in one language to a vector of fixed dimensionality and then map that vector to an output sequence in another language without any human intervention provided that there is enough training data. Focusing on English-French translation, in this paper, I present a way to simplify the learning process by replacing English input sentences by word-by-word translation of those sentences. I found that this approach improves the performance of a sequence-to-sequence model which is 3-layer deep and has a bidirectional LSTM encoder by more than 30% on the same dataset.