OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A6LSN4EBX" target="_blank" >RIV/00216208:11320/25:6LSN4EBX - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85197921089&partnerID=40&md5=e683aa657d68ec040f7c0223264c84f4" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85197921089&partnerID=40&md5=e683aa657d68ec040f7c0223264c84f4</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining

Original language description

Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. However, this method usually randomly initializes the embeddings of new subwords and introduces substantially more embedding parameters to the model, thus weakening the efficiency. To address these issues, we propose a novel framework: One For All (OFA), which wisely initializes the embeddings of unseen subwords and thus can adapt a PLM to multiple languages efficiently and effectively. OFA takes advantage of external well-aligned multilingual static word vectors and injects the alignment knowledge into the subword embeddings. In addition, OFA applies matrix factorization and replaces the cumbersome embeddings with two lower-dimensional matrices, which largely reduces the number of parameters. We show OFA accelerates the convergence of continued pretraining, which is environmentally friendly as much fewer carbon footprints are generated. Through extensive experiments, we demonstrate OFA can achieve competitive or better performance than default continued pretraining baselines on a wide range of crosslingual downstream tasks. We make our code and models publicly available. © 2024 Association for Computational Linguistics.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2024

Confidentiality

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

Article name in the collection

Find. Assoc. Comput. Linguist.: NAACL - Findings

ISBN

979-889176119-3

ISSN

—

e-ISSN

—

Number of pages

31

Pages from-to

1067-1097

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

Mexico City, Mexico

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—