The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models

Abstract

In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicly available models by fine-tuning them on five NLP tasks spanning 12 datasets. Our results suggest that the variant proximity of pre-training data to fine-tuning data is more important than the pre-training data size. We exploit this insight in defining an optimized system selection model for the studied tasks.

arXiv commentAccepted to WANLP 2021

References in corpus (5)

• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• AraBERT: Transformer-based Model for Arabic Language Understanding
• Arabic Dialect Identification in the Wild
• When Do You Need Billions of Words of Pretraining Data?
• Learning meters of Arabic and English poems with Recurrent Neural Networks: a step forward for language understanding and synthesis

Cited by in corpus (2)

• ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD
• Rosetta Stone at KSAA-RD Shared Task: A Hop From Language Modeling To Word--Definition Alignment