Classification-based RNN machine translation using GRUs
This is an incremental approach to machine translation for NLP researchers.
The authors tackled machine translation by developing a classification-based recurrent neural network model using gated recurrent units, which achieved modest results with significant room for improvement.
We report the results of our classification-based machine translation model, built upon the framework of a recurrent neural network using gated recurrent units. Unlike other RNN models that attempt to maximize the overall conditional log probability of sentences against sentences, our model focuses a classification approach of estimating the conditional probability of the next word given the input sequence. This simpler approach using GRUs was hoped to be comparable with more complicated RNN models, but achievements in this implementation were modest and there remains a lot of room for improving this classification approach.