TRANSLICO: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AJDZ2F383" target="_blank" >RIV/00216208:11320/25:JDZ2F383 - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204460367&partnerID=40&md5=7b76eb9093384688f8014917ce561509" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204460367&partnerID=40&md5=7b76eb9093384688f8014917ce561509</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

TRANSLICO: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models

Original language description

The world's more than 7000 languages are written in at least 293 scripts. Due to various reasons, many closely related languages use different scripts, which poses a difficulty for multilingual pretrained language models (mPLMs) in learning crosslingual knowledge through lexical overlap. As a consequence, mPLMs are faced with a script barrier: representations from different scripts are located in different subspaces, which can result in crosslingual transfer involving languages of different scripts performing suboptimally. To address this problem, we propose TRANSLICO, a framework that optimizes the Transliteration Contrastive Modeling (TCM) objective to fine-tune an mPLM by contrasting sentences in its training data and their transliterations in a unified script (in our case Latin), which enhances uniformity in the representation space for different scripts. Using Glot500-m (ImaniGooghari et al., 2023), an mPLM pretrained on over 500 languages, as our source model, we fine-tune it on a small portion (5%) of its training data, and refer to the resulting model as FURINA. We show that FURINA not only better aligns representations from distinct scripts but also outperforms the original Glot500-m on various zero-shot crosslingual transfer tasks. Additionally, we achieve consistent improvement in a case study on the Indic group where the languages exhibit areal features but use different scripts. 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

Proc. Annu. Meet. Assoc. Comput Linguist.

ISBN

979-889176094-3

ISSN

0736-587X

e-ISSN

—

Number of pages

24

Pages from-to

2476-2499

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

Bangkok

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—