Abstract
Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a subword-level encoder on WMT’15 DE-EN and CS-EN, and gives comparable performance on FI-EN and RU-EN. We then demonstrate that it is possible to share a single character-level encoder across multiple languages by training a model on a many-to-one translation task. In this multilingual setting, the character-level encoder significantly outperforms the subword-level encoder on all the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of the BLEU score and human judgment.- Anthology ID:
- Q17-1026
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 5
- Month:
- Year:
- 2017
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 365–378
- Language:
- URL:
- https://aclanthology.org/Q17-1026
- DOI:
- 10.1162/tacl_a_00067
- Cite (ACL):
- Jason Lee, Kyunghyun Cho, and Thomas Hofmann. 2017. Fully Character-Level Neural Machine Translation without Explicit Segmentation. Transactions of the Association for Computational Linguistics, 5:365–378.
- Cite (Informal):
- Fully Character-Level Neural Machine Translation without Explicit Segmentation (Lee et al., TACL 2017)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/Q17-1026.pdf
- Code
- nyu-dl/dl4mt-c2c + additional community code