Abstract
We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence.- Anthology ID:
- W18-2709
- Volume:
- Proceedings of the 2nd Workshop on Neural Machine Translation and Generation
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Alexandra Birch, Andrew Finch, Thang Luong, Graham Neubig, Yusuke Oda
- Venue:
- NGT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 74–83
- Language:
- URL:
- https://aclanthology.org/W18-2709
- DOI:
- 10.18653/v1/W18-2709
- Cite (ACL):
- Huda Khayrallah and Philipp Koehn. 2018. On the Impact of Various Types of Noise on Neural Machine Translation. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 74–83, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- On the Impact of Various Types of Noise on Neural Machine Translation (Khayrallah & Koehn, NGT 2018)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/W18-2709.pdf