Large Language Models as a Normalizer for Transliteration and Dialectal Translation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3ACJZ24EBH" target="_blank" >RIV/00216208:11320/26:CJZ24EBH - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Large Language Models as a Normalizer for Transliteration and Dialectal Translation
Original language description
NLP models trained on standardized language data often struggle with non-standard variations. We assess various Large Language Models (LLMs) for transliteration and dialectal normalization. Tuning open-source LLMs with as little as 10,000 parallel examples using LoRA can achieve results comparable to or better than closed-source LLMs. We perform dialectal normalization experiments for twelve South Asian languages and dialectal translation experiments for six language continua worldwide. The dialectal normalization task can also be a preliminary step for the downstream dialectal translation task. Among the six languages used in dialectal translation, our approach enables Italian and Swiss German to surpass the baseline model by 21.5 and 25.8 BLEU points, respectively. © 2025 Association for Computational Linguistics.
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
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
VarDial - Workshop NLP Similar Lang., Var. Dialects, Proc. Workshop
ISBN
979-8-89176-208-4
ISSN
—
e-ISSN
—
Number of pages
29
Pages from-to
39-67
Publisher name
Association for Computational Linguistics (ACL)
Place of publication
—
Event location
Abu Dhabi
Event date
Jan 1, 2026
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—