Abstract
The encoder-decoder with attention model has become the state of the art for machine translation. However, more investigations are still needed to understand the internal mechanism of this end-to-end model. In this paper, we focus on how neural machine translation (NMT) models consider source information while decoding. We propose a numerical measurement of source context dependency in the NMT models and analyze the behaviors of the NMT decoder with this measurement under several circumstances. Experimental results show that this measurement is an appropriate estimate for source context dependency and consistent over different domains.- Anthology ID:
- 2018.eamt-main.19
- Volume:
- Proceedings of the 21st Annual Conference of the European Association for Machine Translation
- Month:
- May
- Year:
- 2018
- Address:
- Alicante, Spain
- Editors:
- Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada
- Venue:
- EAMT
- SIG:
- Publisher:
- Note:
- Pages:
- 209–218
- Language:
- URL:
- https://aclanthology.org/2018.eamt-main.19
- DOI:
- Cite (ACL):
- Xutai Ma, Ke Li, and Philipp Koehn. 2018. An Analysis of Source Context Dependency in Neural Machine Translation. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, pages 209–218, Alicante, Spain.
- Cite (Informal):
- An Analysis of Source Context Dependency in Neural Machine Translation (Ma et al., EAMT 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2018.eamt-main.19.pdf