arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08671cs.CLcs.LGstat.ML
收藏

预训练或不预训练:检查资源丰富的任务预训练的好处

To Pretrain or Not to Pretrain: Examining the Benefits of Pretraining on Resource Rich Tasks

Faceboook AI(脸书人工智能实验室)

Sinong Wang, Madian Khabsa, Hao Ma

摘要:

使用Masked语言模型(MLM)目标的变体预训练NLP模型最近在许多任务上都有了显着的改进。本文研究了预训练模型作为下游任务中使用的训练样本数量的函数的好处。在几个文本分类任务中,我们发现,随着训练样本的数量增长到数百万,微调基于BERT的模型和从头开始训练普通LSTM之间的准确率差距缩小到1%以内。我们的研究结果表明,基于MLM的模型可能会达到一个收益递减点,因为监督数据的大小显着增加。

英文摘要:

Pretraining NLP models with variants of Masked Language Model (MLM) objectives has recently led to a significant improvements on many tasks. This paper examines the benefits of pretrained models as a function of the number of training samples used in the downstream task. On several text classification tasks, we show that as the number of training examples grow into the millions, the accuracy gap between finetuning BERT-based model and training vanilla LSTM from scratch narrows to within 1%. Our findings indicate that MLM-based models might reach a diminishing return point as the supervised data size increases significantly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑