Exploring the Impact of Transliteration on NLP Performance: Treating Maltese as an Arabic Dialect

Kurt Micallef, Fadhl Eryani, Nizar Habash, Houda Bouamor, Claudia Borg

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Multilingual models such as mBERT have been demonstrated to exhibit impressive cross-lingual transfer for a number of languages. Despite this, the performance drops for lower-resourced languages, especially when they are not part of the pre-training setup and when there are script differences. In this work we consider Maltese, a low-resource language of Arabic and Romance origins written in Latin script. Specifically, we investigate the impact of transliterating Maltese into Arabic scipt on a number of downstream tasks: Part-of-Speech Tagging, Dependency Parsing, and Sentiment Analysis. We compare multiple transliteration pipelines ranging from deterministic character maps to more sophisticated alternatives, including manually annotated word mappings and non-deterministic character mappings. For the latter, we show that selection techniques using n-gram language models of Tunisian Arabic, the dialect with the highest degree of mutual intelligibility to Maltese, yield better results on downstream tasks. Moreover, our experiments highlight that the use of an Arabic pre-trained model paired with transliteration outperforms mBERT. Overall, our results show that transliterating Maltese can be considered an option to improve the cross-lingual transfer capabilities.

Original languageEnglish (US)
Title of host publicationWorkshop on Computation and Written Language, CAWL 2023 - Proceedings of the Workshop
EditorsKyle Gorman, Brian Roark, Richard Sproat
PublisherAssociation for Computational Linguistics (ACL)
Number of pages11
ISBN (Electronic)9781959429906
StatePublished - 2023
Event2023 Workshop on Computation and Written Language, CAWL 2023 - Toronto, Canada
Duration: Jul 14 2023 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X


Conference2023 Workshop on Computation and Written Language, CAWL 2023
Period7/14/23 → …

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics


Dive into the research topics of 'Exploring the Impact of Transliteration on NLP Performance: Treating Maltese as an Arabic Dialect'. Together they form a unique fingerprint.

Cite this