Next-Level Cantonese-to-Mandarin Translation: Fine-Tuning and Post-Processing with LLMs

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AWJSDKG3K" target="_blank" >RIV/00216208:11320/26:WJSDKG3K - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Next-Level Cantonese-to-Mandarin Translation: Fine-Tuning and Post-Processing with LLMs

Original language description

Large Language Models (LLMs) have improved performance across various natural language processing tasks. Despite these improvements, LLMs continue to face significant challenges, such as grammatical issues and code-switching to English, when applied to low-resource languages like Cantonese in Machine Translation (MT) scenarios. By addressing the unique linguistic and contextual challenges of Cantonese, we present a novel strategy to improve the understanding and translation capabilities of LLMs for Cantonese-to-Mandarin MT. Our strategy comprises three key components: (1) Syntax and Part-of-Speech (POS) fine-tuning, where we use the Universal Dependencies (UD) corpus to fine-tune LLM, focusing on the linguistic structures of Cantonese; (2) Specialized Cantonese to Mandarin sentence pairs, collected from diverse sources such as Cantonese grammar textbooks and manually translated sentences across various domains, to expose the model to a wide range of linguistic contexts; (3) Post-processing with additional LLMs, where we introduce additional LLMs to improve the initial translations, correcting Mandarin grammar and punctuation. Empirical evaluations on human-created test sets show that our proposed strategy improves translation performance and outperforms existing commercial translation models with at least 3 BLEU scores. Additionally, our strategy also benefits other LLMs and a reversed translation direction, demonstrating its generalization and effectiveness. © 2025 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

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proc. Main Conf. Int. Conf. Comput. Linguist., COLING

ISBN

979-8-89176-215-2

ISSN

—

e-ISSN

—

Number of pages

10

Pages from-to

427-436

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

—