Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task
Show others and affiliations
2021 (English)In: Proceedings of the 8th Workshop on Asian Translation (WAT2021), Association for Computational Linguistics, 2021, p. 205-211Conference paper, Published paper (Refereed)
Abstract [en]

This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization. We train and evaluate large multilingual translation models using a single GPU for a maximum of 100 hours and get within 4-5 BLEU points of the top submission on the leaderboard. We also benchmark standard baselines on the PMI corpus and re-discover well-known shortcomings of translation systems and metrics.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2021. p. 205-211
National Category
Natural Language Processing
Identifiers
URN: urn:nbn:se:hj:diva-54862DOI: 10.18653/v1/2021.wat-1.24OAI: oai:DiVA.org:hj-54862DiVA, id: diva2:1603511
Conference
8th Workshop on Asian Translation (WAT2021)
Available from: 2021-10-15 Created: 2021-10-15 Last updated: 2025-02-07

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textACL Anthology

Search in DiVA

By author/editor
Bollmann, Marcel
By organisation
Jönköping AI Lab (JAIL)
Natural Language Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 131 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf