Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations, but incurs substantial training costs. In this paper, we propose a novel concept-based curriculum masking (CCM) method to efficiently pre-train a language model. CCM has two key differences from existing curriculum learning approaches to effectively reflect the nature of MLM. First, we introduce a carefully-designed linguistic difficulty criterion that evaluates the MLM difficulty of each token. Second, we construct a curriculum that gradually masks words related to the previously masked words by retrieving a knowledge graph. Experimental results show that CCM significantly improves pre-training efficiency. Specifically, the model trained with CCM shows comparative performance with the original BERT on the General Language Understanding Evaluation benchmark at half of the training cost.
@article{arxiv.2212.07617,
title = {Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking},
author = {Mingyu Lee and Jun-Hyung Park and Junho Kim and Kang-Min Kim and SangKeun Lee},
journal= {arXiv preprint arXiv:2212.07617},
year = {2022}
}