Exploring the Impact of Transliteration on NLP Performance for Low-Resource Languages: The Case of Maltese and Arabic
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A8VCVDYV8" target="_blank" >RIV/00216208:11320/23:8VCVDYV8 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2023.cawl-1.4/" target="_blank" >https://aclanthology.org/2023.cawl-1.4/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2023.cawl-1.4" target="_blank" >10.18653/v1/2023.cawl-1.4</a>
Alternative languages
Result language
angličtina
Original language name
Exploring the Impact of Transliteration on NLP Performance for Low-Resource Languages: The Case of Maltese and Arabic
Original language description
"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."
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
—
Continuities
—
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
"Proceedings of the Workshop on Computation and Written Language (CAWL 2023)"
ISBN
978-1-959429-90-6
ISSN
—
e-ISSN
—
Number of pages
11
Pages from-to
22-32
Publisher name
""
Place of publication
Toronto, Canada
Event location
Toronto, Canada
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—