Abstract
Despite its promise, neural machine translation (NMT) has a serious problem in that source content may be mistakenly left untranslated. The ability to detect untranslated content is important for the practical use of NMT. We evaluate two types of probability with which to detect untranslated content: the cumulative attention (ATN) probability and back translation (BT) probability from the target sentence to the source sentence. Experiments on detecting untranslated content in Japanese-English patent translations show that ATN and BT are each more effective than random choice, BT is more effective than ATN, and the combination of the two provides further improvements. We also confirmed the effectiveness of using ATN and BT to rerank the n-best NMT outputs.- Anthology ID:
- W17-3206
- Volume:
- Proceedings of the First Workshop on Neural Machine Translation
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver
- Editors:
- Thang Luong, Alexandra Birch, Graham Neubig, Andrew Finch
- Venue:
- NGT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 47–55
- Language:
- URL:
- https://aclanthology.org/W17-3206
- DOI:
- 10.18653/v1/W17-3206
- Cite (ACL):
- Isao Goto and Hideki Tanaka. 2017. Detecting Untranslated Content for Neural Machine Translation. In Proceedings of the First Workshop on Neural Machine Translation, pages 47–55, Vancouver. Association for Computational Linguistics.
- Cite (Informal):
- Detecting Untranslated Content for Neural Machine Translation (Goto & Tanaka, NGT 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W17-3206.pdf