Abstract
The machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality. How much quality to sacrifice for efficiency depends upon the application, so participants were encouraged to make multiple submissions covering the space of trade-offs. In total, there were 53 submissions by 4 teams. There were GPU, single-core CPU, and multi-core CPU hardware tracks as well as batched throughput or single-sentence latency conditions. Submissions showed hundreds of millions of words can be translated for a dollar, average latency is 5–17 ms, and models fit in 7.5–150 MB.- Anthology ID:
- 2021.wmt-1.68
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 639–651
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.68
- DOI:
- Cite (ACL):
- Kenneth Heafield, Qianqian Zhu, and Roman Grundkiewicz. 2021. Findings of the WMT 2021 Shared Task on Efficient Translation. In Proceedings of the Sixth Conference on Machine Translation, pages 639–651, Online. Association for Computational Linguistics.
- Cite (Informal):
- Findings of the WMT 2021 Shared Task on Efficient Translation (Heafield et al., WMT 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.wmt-1.68.pdf