Low-Resource Machine Translation Systems for Indic Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475723" target="_blank" >RIV/00216208:11320/23:10475723 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Low-Resource Machine Translation Systems for Indic Languages

Popis výsledku v původním jazyce

We present the submission of the CUNI team to the WMT23 shared task in translation between English and Assamese, Khasi, Mizo, and Manipuri. All our systems were pretrained on the task of multilingual masked language modelling and denoising auto-encoding. Our primary systems for translation into English were further pretrained for multilingual MT in all four language directions and fine-tuned on the limited parallel data available for each language pair separately. We used online back-translation for data augmentation. The same systems were submitted as contrastive for translation out of English where the multilingual MT pretraining step seemed to harm the translation performance. Other contrastive systems used additional pseudo-parallel data mined from monolingual corpora.

Název v anglickém jazyce

Low-Resource Machine Translation Systems for Indic Languages

Popis výsledku anglicky

We present the submission of the CUNI team to the WMT23 shared task in translation between English and Assamese, Khasi, Mizo, and Manipuri. All our systems were pretrained on the task of multilingual masked language modelling and denoising auto-encoding. Our primary systems for translation into English were further pretrained for multilingual MT in all four language directions and fine-tuned on the limited parallel data available for each language pair separately. We used online back-translation for data augmentation. The same systems were submitted as contrastive for translation out of English where the multilingual MT pretraining step seemed to harm the translation performance. Other contrastive systems used additional pseudo-parallel data mined from monolingual corpora.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Eighth Conference on Machine Translation

ISBN

979-8-89176-041-7

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

954-958

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Singapore, Singapore

Datum konání akce

6. 12. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—