Abstract
Translating in real-time, a.k.a.simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment. To trade off quality and delay, we extensively explore various targets for delay and design a method for beam-search applicable in the simultaneous MT setting. Experiments against state-of-the-art baselines on two language pairs demonstrate the efficacy of the proposed framework both quantitatively and qualitatively.- Anthology ID:
- E17-1099
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1053–1062
- Language:
- URL:
- https://aclanthology.org/E17-1099
- DOI:
- Cite (ACL):
- Jiatao Gu, Graham Neubig, Kyunghyun Cho, and Victor O.K. Li. 2017. Learning to Translate in Real-time with Neural Machine Translation. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 1053–1062, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Learning to Translate in Real-time with Neural Machine Translation (Gu et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/E17-1099.pdf
- Code
- nyu-dl/dl4mt-simul-trans