Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/114786
Title: | Exploring the impact of transliteration on NLP performance : treating Maltese as an Arabic dialect |
Authors: | Micallef, Kurt Eryani, Fadhl Habash, Nizar Bouamor, Houda Borg, Claudia |
Keywords: | Text processing (Computer science) -- Malta Transliteration Artificial intelligence Translating and interpreting -- Technological innovations |
Issue Date: | 2023 |
Publisher: | Association for Computational Linguistics |
Citation: | Micallef, K., Eryani, F., Habash, N., Bouamor, H. & Borg, C. (2023). Exploring the Impact of Transliteration on NLP Performance: Treating Maltese as an Arabic Dialect. Workshop on Computation and Written Language (CAWL 2023), Toronto. 22-32. |
Abstract: | Multilingual models such as mBERT have been demonstrated to exhibit impressive crosslingual transfer for a number of languages. Despite this, the performance drops for lowerresourced 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. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/114786 |
Appears in Collections: | Scholarly Works - FacICTAI |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2023.cawl-1.4.pdf | 449.16 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.