Replacement of Unknown Words Using an Attention Model in Japanese to English Neural Machine Translation

Abstract

It is well known that machine translation using recurrent neural networks often composes fluent sentences but may include many unknown words. Although there have been many works to address the unknown word problem, they are ineffective in Japanese to English translation. In this study, we propose a hybrid method that makes an alignment table using an attention weight matrix, detects input words that are aligned with each unknown words, and finally replaces those unknown words with the translated words using a statistical machine translation method. We evaluate our approach by using two corpora: ASPEC and NTCIR-10. The results showed that the proposed method generated no unknown words and improved the BLEU (BiLingual Evaluation Understudy) score.