conference-paper
Open access
What do Neural Machine Translation Models Learn about Morphology?
Research footprint
At a glance
- Citations
- 283
- References
- 53
- Comments
- 0
Paper overview
Abstract
Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process.
Record transparency
Publication details
- DOI
- 10.18653/v1/p17-1080
- OpenAlex
- W2605717780
- Document type
- conference-paper
- Language
- EN
- Last metadata update
Comments
Log in to join the discussion.