2025-01-14-fang25a.md

title	MLCL: A Framework for Reducing Language Imbalance in Sino-Tibetan Languages through Adapter Structures
booktitle	Proceedings of the 16th Asian Conference on Machine Learning
year	2025
volume	260
series	Proceedings of Machine Learning Research
month	0
publisher	PMLR
pdf	https://raw.githubusercontent.com/mlresearch/v260/main/assets/fang25a/fang25a.pdf
url	https://proceedings.mlr.press/v260/fang25a.html
openreview	s9yXKcsKbP
abstract	Multilingual pre-trained models have been widely applied in natural language processing (NLP) tasks, including text classification. However, due to the varying amounts of language resources, these models exhibit performance imbalance across different languages, a phenomenon known as language imbalance. Existing research on mitigating language imbalance primarily harnesses text and image data, neglecting the auditory aspects of languages. This neglect results in an incomplete solution to language imbalance, as it fails to exploit the rich linguistic nuances conveyed through speech. To address these issues, this paper introduces a novel framework called MultiLingual Contrastive Learning (MLCL) to reduce language imbalance. By incorporating concepts from comparative linguistics into neural networks, we utilize the phonetic similarities among languages within the Sino-Tibetan family to tackle the problem of language imbalance in multilingual pre-trained models. To evaluate our method’s effectiveness, we conducted tests using two synthetic datasets derived from the Flores200 and mms datasets across various models. The experimental results show that, in terms of language imbalance metrics, our model surpasses all baseline models.
layout	inproceedings
issn	2640-3498
id	fang25a
tex_title	{MLCL}: {A} Framework for Reducing Language Imbalance in Sino-Tibetan Languages through Adapter Structures
firstpage	431
lastpage	446
page	431-446
order	431
cycles	false
bibtex_editor	Nguyen, Vu and Lin, Hsuan-Tien
editor	given family Vu Nguyen given family Hsuan-Tien Lin
bibtex_author	Fang, JiaJun and Huang, Wentao and Yang, Aimin and Zhou, Dong and Lin, Nankai
author	given family JiaJun Fang given family Wentao Huang given family Aimin Yang given family Dong Zhou given family Nankai Lin
date	2025-01-14
address
container-title	Proceedings of the 16th Asian Conference on Machine Learning
genre	inproceedings
issued	date-parts 2025 1 14
extras