Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A9JIGNYMT" target="_blank" >RIV/00216208:11320/25:9JIGNYMT - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189936129&partnerID=40&md5=10f464c8653f4e7a6b1426906acb279a" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189936129&partnerID=40&md5=10f464c8653f4e7a6b1426906acb279a</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching

Original language description

Although multilingual language models exhibit impressive cross-lingual transfer capabilities on unseen languages, the performance on downstream tasks is impacted when there is a script disparity with the languages used in the multilingual model's pre-training data. Using transliteration offers a straightforward yet effective means to align the script of a resource-rich language with a target language, thereby enhancing cross-lingual transfer capabilities. However, for mixed languages, this approach is suboptimal, since only a subset of the language benefits from the cross-lingual transfer while the remainder is impeded. In this work, we focus on Maltese, a Semitic language, with substantial influences from Arabic, Italian, and English, and notably written in Latin script. We present a novel dataset annotated with word-level etymology. We use this dataset to train a classifier that enables us to make informed decisions regarding the appropriate processing of each token in the Maltese language. We contrast indiscriminate transliteration or translation to mixing processing pipelines that only transliterate words of Arabic origin, thereby resulting in text with a mixture of scripts. We fine-tune the processed data on four downstream tasks and show that conditional transliteration based on word etymology yields the best results, surpassing finetuning with raw Maltese or Maltese processed with non-selective pipelines. © 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

EACL - Conf. European Chapter Assoc. Comput. Linguist., Proc. Conf.

ISBN

979-889176088-2

ISSN

—

e-ISSN

—

Number of pages

12

Pages from-to

1014-1025

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

St. Julian's

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—