MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning
Abstract
Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. In this work, we investigate two techniques for training monolingual TLMs in a low-resource setting: greatly reducing TLM size, and complementing the masked language modeling objective with two linguistically rich supervised tasks (part-of-speech tagging and dependency parsing). Results from 7 diverse languages indicate that our model, MicroBERT, is able to produce marked improvements in downstream task evaluations relative to a typical monolingual TLM pretraining approach. Specifically, we find that monolingual MicroBERT models achieve gains of up to 18% for parser LAS and 11% for NER F1 compared to a multilingual baseline, mBERT, while having less than 1% of its parameter count. We conclude reducing TLM parameter count and using labeled data for pretraining low-resource TLMs can yield large quality benefits and in some cases produce models that outperform multilingual approaches.
Cite
@article{arxiv.2212.12510,
title = {MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning},
author = {Luke Gessler and Amir Zeldes},
journal= {arXiv preprint arXiv:2212.12510},
year = {2023}
}
Comments
Presented at MRL at EMNLP 2022 in Abu Dhabi. Code at https://github.com/lgessler/microbert and models at https://huggingface.co/lgessler