English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor
This is an incremental improvement for machine translation researchers and practitioners, addressing specific translation quality issues in a domain-specific context.
The paper tackles the problem of repeating or missing words in neural machine translation by applying an encoder-decoder-reconstructor framework with back-translation to English-Japanese translation, confirming improvements in BLEU scores and alleviating these issues.
Neural machine translation (NMT) has recently become popular in the field of machine translation. However, NMT suffers from the problem of repeating or missing words in the translation. To address this problem, Tu et al. (2017) proposed an encoder-decoder-reconstructor framework for NMT using back-translation. In this method, they selected the best forward translation model in the same manner as Bahdanau et al. (2015), and then trained a bi-directional translation model as fine-tuning. Their experiments show that it offers significant improvement in BLEU scores in Chinese-English translation task. We confirm that our re-implementation also shows the same tendency and alleviates the problem of repeating and missing words in the translation on a English-Japanese task too. In addition, we evaluate the effectiveness of pre-training by comparing it with a jointly-trained model of forward translation and back-translation.