SwePub
Sök i LIBRIS databas

  Extended search

WFRF:(Reid David)
 

Search: WFRF:(Reid David) > (2020-2024) > A Few Thousand Tran...

A Few Thousand Translations Go A Long Way! Leveraging Pre-trained Models for African News Translation

Adelani, David (author)
Saarland Univ, Saarbrucken, Germany.
Alabi, Jesujoba (author)
INRIA, Paris, France.
Fan, Angela (author)
Meta AI, Menlo Pk, CA USA.
show more...
Kreutzer, Julia (author)
Google Res, Mountain View, CA USA.
Shen, Xiaoyu (author)
Amazon Alexa AI, Seattle, WA USA.
Reid, Machel (author)
Univ Tokyo, Tokyo, Japan.
Ruiter, Dana (author)
Saarland Univ, Saarbrucken, Germany.
Klakow, Dietrich (author)
Saarland Univ, Saarbrucken, Germany.
Nabende, Peter (author)
Makerere Univ, Kampala, Uganda.
Chang, Ernie (author)
Saarland Univ, Saarbrucken, Germany.
Gwadabe, Tajuddeen (author)
UCAS, Beijing, Peoples R China.
Sackey, Freshia (author)
JKUAT, Juja, Kenya.
Dossou, Bonaventure F. P. (author)
Jacobs Univ, Bremen, Germany.
Emezue, Chris (author)
TUM, Munich, Germany.
Leong, Colin (author)
Univ Dayton, Dayton, OH 45469 USA.
Beukman, Michael (author)
Univ Witwatersrand, Johannesburg, South Africa.
Muhammad, Shamsuddeen (author)
LIAAD INESC TEC, Porto, Portugal.
Jarso, Guyo (author)
Yousuf, Oreen (author)
Uppsala universitet,Institutionen för lingvistik och filologi
Rubungo, Andre Niyongabo (author)
UPC, Barcelona, Spain.
Hacheme, Gilles (author)
Ai4Innov, Paris, France.
Wairagala, Eric Peter (author)
Makerere Univ, Kampala, Uganda.
Nasir, Muhammad Umair (author)
Ominor AI, Orlando, FL USA.
Ajibade, Benjamin (author)
Ajayi, Tunde (author)
Gitau, Yvonne (author)
Abbott, Jade (author)
Ahmed, Mohamed (author)
Microsoft Africa Res Inst, Nairobi, Kenya.
Ochieng, Millicent (author)
Microsoft Africa Res Inst, Nairobi, Kenya.
Aremu, Anuoluwapo (author)
Ogayo, Perez (author)
CMU, Pittsburgh, PA USA.
Mukiibi, Jonathan (author)
Makerere Univ, Kampala, Uganda.
Kabore, Fatoumata Ouoba (author)
Kalipe, Godson (author)
Mbaye, Derguene (author)
Baamtu, Dakar, Senegal.
Tapo, Allahsera Auguste (author)
RIT, Rochester, NY USA.
Koagne, Victoire Memdjokam (author)
Munkoh-Buabeng, Edwin (author)
Wagner, Valencia (author)
SPU, Kimberley, South Africa.
Abdulmumin, Idris (author)
ABU, Abuja, Nigeria.
Awokoya, Ayodele (author)
UI Ibadan, Ibadan, Nigeria.
Buzaaba, Happy (author)
Sibanda, Blessing (author)
NUST, Windhoek, Namibia.
Bukula, Andiswa (author)
SADiLaR, Potchefstroom, South Africa.
Manthalu, Sam (author)
Univ Malawi, Zomba, Malawi.
show less...
Saarland Univ, Saarbrucken, Germany INRIA, Paris, France. (creator_code:org_t)
Stroudsburg : Association for Computational Linguistics, 2022
2022
English.
In: NAACL 2022. - Stroudsburg : Association for Computational Linguistics. - 9781955917711 ; , s. 3053-3070
  • Conference paper (peer-reviewed)
Abstract Subject headings
Close  
  • Recent advances in the pre-training of language models leverage large-scale datasets to create multilingual models. However, low-resource languages are mostly left out in these datasets. This is primarily because many widely spoken languages are not well represented on the web and therefore excluded from the large-scale crawls used to create datasets. Furthermore, downstream users of these models are restricted to the selection of languages originally chosen for pre-training. This work investigates how to optimally leverage existing pre-trained models to create low-resource translation systems for 16 African languages. We focus on two questions: 1) How can pre-trained models be used for languages not included in the initial pre-training? and 2) How can the resulting translation models effectively transfer to new domains? To answer these questions, we create a new African news corpus covering 16 languages, of which eight languages are not part of any existing evaluation dataset. We demonstrate that the most effective strategy for transferring both to additional languages and to additional domains is to fine-tune large pre-trained models on small quantities of high-quality translation data.

Subject headings

NATURVETENSKAP  -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
NATURAL SCIENCES  -- Computer and Information Sciences -- Language Technology (hsv//eng)

Publication and Content Type

ref (subject category)
kon (subject category)

Find in a library

  • NAACL 2022 (Search for host publication in LIBRIS)

To the university's database

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Close

Copy and save the link in order to return to this view