Findings of the WMT 2021 Shared Task on Efficient Translation

Kenneth Heafield; Qianqian Zhu; Roman Grundkiewicz

Findings of the WMT 2021 Shared Task on Efficient Translation

Kenneth Heafield, Qianqian Zhu, Roman Grundkiewicz

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

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.

Original language	English
Title of host publication	Proceedings of the Sixth Conference on Machine Translation
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics
Pages	639-651
Number of pages	13
ISBN (Print)	978-1-954085-94-7
Publication status	Published - 10 Nov 2021
Event	Sixth Conference on Machine Translation - Punta Cana, Dominican Republic Duration: 10 Nov 2021 → 11 Nov 2021 Conference number: 6 https://www.statmt.org/wmt21/

Conference

Conference	Sixth Conference on Machine Translation
Abbreviated title	WMT21
Country/Territory	Dominican Republic
City	Punta Cana
Period	10/11/21 → 11/11/21
Internet address	https://www.statmt.org/wmt21/

Access to Document

Findings of the WMT_HEAFIELD_DOA05092021_VOR_CC-BYFinal published version, 289 KBLicence: Creative Commons: Attribution (CC-BY)

https://aclanthology.org/2021.wmt-1.68Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{706a0e1763d64cefbf7ff5f806e69405,

title = "Findings of the WMT 2021 Shared Task on Efficient Translation",

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.",

author = "Kenneth Heafield and Qianqian Zhu and Roman Grundkiewicz",

year = "2021",

month = nov,

day = "10",

language = "English",

isbn = "978-1-954085-94-7",

pages = "639--651",

booktitle = "Proceedings of the Sixth Conference on Machine Translation",

publisher = "Association for Computational Linguistics",

note = "Sixth Conference on Machine Translation, WMT21 ; Conference date: 10-11-2021 Through 11-11-2021",

url = "https://www.statmt.org/wmt21/",

}

Heafield, K, Zhu, Q & Grundkiewicz, R 2021, Findings of the WMT 2021 Shared Task on Efficient Translation. in Proceedings of the Sixth Conference on Machine Translation. Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 639-651, Sixth Conference on Machine Translation, Punta Cana, Dominican Republic, 10/11/21. <https://aclanthology.org/2021.wmt-1.68>

TY - GEN

T1 - Findings of the WMT 2021 Shared Task on Efficient Translation

AU - Heafield, Kenneth

AU - Zhu, Qianqian

AU - Grundkiewicz, Roman

N1 - Conference code: 6

PY - 2021/11/10

Y1 - 2021/11/10

N2 - 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.

AB - 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.

M3 - Conference contribution

SN - 978-1-954085-94-7

SP - 639

EP - 651

BT - Proceedings of the Sixth Conference on Machine Translation

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

T2 - Sixth Conference on Machine Translation

Y2 - 10 November 2021 through 11 November 2021

ER -

Findings of the WMT 2021 Shared Task on Efficient Translation

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this