Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cruz, Jan Christian Blaise, Aji, Alham Fikri
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915115559813120
author Cruz, Jan Christian Blaise
Aji, Alham Fikri
author_facet Cruz, Jan Christian Blaise
Aji, Alham Fikri
contents In this paper, we propose the use of simple knowledge distillation to produce smaller and more efficient single-language transformers from Massively Multilingual Transformers (MMTs) to alleviate tradeoffs associated with the use of such in low-resource settings. Using Tagalog as a case study, we show that these smaller single-language models perform on-par with strong baselines in a variety of benchmark tasks in a much more efficient manner. Furthermore, we investigate additional steps during the distillation process that improves the soft-supervision of the target language, and provide a number of analyses and ablations to show the efficacy of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12660
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation
Cruz, Jan Christian Blaise
Aji, Alham Fikri
Computation and Language
In this paper, we propose the use of simple knowledge distillation to produce smaller and more efficient single-language transformers from Massively Multilingual Transformers (MMTs) to alleviate tradeoffs associated with the use of such in low-resource settings. Using Tagalog as a case study, we show that these smaller single-language models perform on-par with strong baselines in a variety of benchmark tasks in a much more efficient manner. Furthermore, we investigate additional steps during the distillation process that improves the soft-supervision of the target language, and provide a number of analyses and ablations to show the efficacy of the proposed method.
title Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation
topic Computation and Language
url https://arxiv.org/abs/2501.12660