Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nezhad, Sina Bagheri, Agrawal, Ameeta, Pokharel, Rhitabrat
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929634990358528
author Nezhad, Sina Bagheri
Agrawal, Ameeta
Pokharel, Rhitabrat
author_facet Nezhad, Sina Bagheri
Agrawal, Ameeta
Pokharel, Rhitabrat
contents Multilingual language models (MLLMs) are crucial for handling text across various languages, yet they often show performance disparities due to differences in resource availability and linguistic characteristics. While the impact of pre-train data percentage and model size on performance is well-known, our study reveals additional critical factors that significantly influence MLLM effectiveness. Analyzing a wide range of features, including geographical, linguistic, and resource-related aspects, we focus on the SIB-200 dataset for classification and the Flores-200 dataset for machine translation, using regression models and SHAP values across 204 languages. Our findings identify token similarity and country similarity as pivotal factors, alongside pre-train data and model size, in enhancing model performance. Token similarity facilitates cross-lingual transfer, while country similarity highlights the importance of shared cultural and linguistic contexts. These insights offer valuable guidance for developing more equitable and effective multilingual language models, particularly for underrepresented languages.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12500
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Models
Nezhad, Sina Bagheri
Agrawal, Ameeta
Pokharel, Rhitabrat
Computation and Language
Artificial Intelligence
Multilingual language models (MLLMs) are crucial for handling text across various languages, yet they often show performance disparities due to differences in resource availability and linguistic characteristics. While the impact of pre-train data percentage and model size on performance is well-known, our study reveals additional critical factors that significantly influence MLLM effectiveness. Analyzing a wide range of features, including geographical, linguistic, and resource-related aspects, we focus on the SIB-200 dataset for classification and the Flores-200 dataset for machine translation, using regression models and SHAP values across 204 languages. Our findings identify token similarity and country similarity as pivotal factors, alongside pre-train data and model size, in enhancing model performance. Token similarity facilitates cross-lingual transfer, while country similarity highlights the importance of shared cultural and linguistic contexts. These insights offer valuable guidance for developing more equitable and effective multilingual language models, particularly for underrepresented languages.
title Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.12500