Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining objectives, e.g., predicting the first character of a masked token, have recently shown comparable results to MLM, no objectives with a masking scheme actually outperform it in downstream tasks. Motivated by the assumption that their lack of complexity plays a vital role in the degradation, we validate whether more complex masked objectives can achieve better results and investigate how much complexity they should have to perform comparably to MLM. Our results using GLUE, SQuAD, and Universal Dependencies benchmarks demonstrate that more complicated objectives tend to show better downstream results with at least half of the MLM complexity needed to perform comparably to MLM. Finally, we discuss how we should pretrain a model using a masked objective from the task complexity perspective.

翻译：掩码语言建模（MLM）是一种广泛使用的自监督预训练目标，要求模型根据上下文预测被掩码替换的原始词元。尽管更简单且计算高效的预训练目标（例如预测掩码词元的首字符）近期展现出与MLM相当的结果，但采用掩码机制的目标实际上均未在下游任务中超越MLM。基于"复杂度不足是导致性能降级的关键因素"这一假设，我们验证了更复杂的掩码目标能否取得更优结果，并探究为实现与MLM相当的性能需达到何种复杂度。基于GLUE、SQuAD和Universal Dependencies基准的实验表明：更复杂的目标往往能获得更好的下游表现，且当复杂度达到MLM的至少一半时即可产生可比性能。最后，我们从任务复杂度视角探讨了如何利用掩码目标预训练模型。