Bi-Decoder Augmented Network for Neural Machine Translation
This addresses the issue of language-independent semantic representations in NMT, which is an incremental improvement over existing encoder-decoder frameworks.
The paper tackles the problem of language-dependent representations in neural machine translation by proposing a Bi-Decoder Augmented Network (BiDAN) that adds an auxiliary decoder to generate back the source language during training, resulting in improved performance on several benchmark datasets.
Neural Machine Translation (NMT) has become a popular technology in recent years, and the encoder-decoder framework is the mainstream among all the methods. It's obvious that the quality of the semantic representations from encoding is very crucial and can significantly affect the performance of the model. However, existing unidirectional source-to-target architectures may hardly produce a language-independent representation of the text because they rely heavily on the specific relations of the given language pairs. To alleviate this problem, in this paper, we propose a novel Bi-Decoder Augmented Network (BiDAN) for the neural machine translation task. Besides the original decoder which generates the target language sequence, we add an auxiliary decoder to generate back the source language sequence at the training time. Since each decoder transforms the representations of the input text into its corresponding language, jointly training with two target ends can make the shared encoder has the potential to produce a language-independent semantic space. We conduct extensive experiments on several NMT benchmark datasets and the results demonstrate the effectiveness of our proposed approach.