Refining the state-of-the-art in Machine Translation, optimizing NMT for the JA <-> EN language pair by leveraging personal domain expertise
This work addresses translation quality for the Japanese-English language pair, but it is incremental as it applies existing methods to this specific domain.
The authors tackled improving neural machine translation for Japanese-English by systematically optimizing a Transformer-based system, achieving unspecified performance gains as measured by BLEU and subjective evaluation.
Documenting the construction of an NMT (Neural Machine Translation) system for En/Ja based on the Transformer architecture leveraging the OpenNMT framework. A systematic exploration of corpora pre-processing, hyperparameter tuning and model architecture is carried out to obtain optimal performance. The system is evaluated using standard auto-evaluation metrics such as BLEU, and my subjective opinion as a Japanese linguist.