Regularized Context Gates on Transformer for Machine Translation
This work addresses a specific problem in machine translation by improving control over source and target contexts in Transformers, representing an incremental advancement.
The paper tackled the challenge of extending context gates to the Transformer architecture for neural machine translation by introducing a gate mechanism and a regularization method to reduce bias, achieving an averaged gain of 1.0 BLEU score over a strong baseline across four datasets.
Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation (NMT). However, it is challenging to extend them into the advanced Transformer architecture, which is more complicated than RNN. This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer. In addition, to further reduce the bias problem in the gate mechanism, this paper proposes a regularization method to guide the learning of the gates with supervision automatically generated using pointwise mutual information. Extensive experiments on 4 translation datasets demonstrate that the proposed model obtains an averaged gain of 1.0 BLEU score over a strong Transformer baseline.