arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05568cs.CL
收藏

作为Meta学习的预训练文本表示

Pre-training Text Representations as Meta Learning

Microsoft Research Asia(微软亚洲研究院);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Science and Technology of China(中国科学技术大学);Sun Yat-sen University(中山大学);Microsoft Corporation(微软公司)

Shangwen Lv, Yuechen Wang, Daya Guo, Duyu Tang, Nan Duan, Fuqing Zhu, Ming Gong, Linjun Shou, Ryan Ma, Daxin Jiang, Guihong Cao, Ming Zhou, Songlin Hu

摘要:

预训练文本表示最近被证明可以显着提高许多自然语言处理任务的最新水平。预训练的中心目标是学习对后续任务有用的文本表示。然而,现有的方法通过最小化代理目标来优化,例如语言建模的负对数似然。在这项工作中,我们引入了一个学习算法,它直接优化模型的学习能力,有效地学习下游任务的文本表示。我们证明了多任务预训练和模型不可知元学习之间存在内在联系,并具有一系列元训练步骤。BERT中采用的标准多任务学习目标是我们的学习算法的一个特例,其中元训练的深度为零。我们在两种情况下研究了该问题:无监督的预训练和有监督的预训练与不同的预训练对象,以验证我们的方法的通用性。实验结果表明,我们的算法带来了改进,学习更好的初始化各种下游任务。

英文摘要:

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for subsequent tasks. However, existing approaches are optimized by minimizing a proxy objective, such as the negative log likelihood of language modeling. In this work, we introduce a learning algorithm which directly optimizes model's ability to learn text representations for effective learning of downstream tasks. We show that there is an intrinsic connection between multi-task pre-training and model-agnostic meta-learning with a sequence of meta-train steps. The standard multi-task learning objective adopted in BERT is a special case of our learning algorithm where the depth of meta-train is zero. We study the problem in two settings: unsupervised pre-training and supervised pre-training with different pre-training objects to verify the generality of our approach.Experimental results show that our algorithm brings improvements and learns better initializations for a variety of downstream tasks.

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。

↑