当前位置: X-MOL 学术ACM SIGMOD Rec. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
TURL: Table Understanding through Representation Learning: ACM SIGMOD Record: Vol 51, No 1
ACM SIGMOD Record ( IF 1.1 ) Pub Date : 2022-06-01 , DOI: 10.1145/3542700.3542709
Xiang Deng, Huan Sun, Alyssa Lees, You Wu, Cong Yu

Relational tables on the Web store a vast amount of knowledge. Owing to the wealth of such tables, there has been tremendous progress on a variety of tasks in the area of table understanding. However, existing work generally relies on heavily-engineered task-specific features and model architectures. In this paper, we present TURL, a novel framework that introduces the pre-training/fine-tuning paradigm to relational Web tables. During pre-training, our framework learns deep contextualized representations on relational tables in a self-supervised manner. Its universal model design with pre-trained representations can be applied to a wide range of tasks with minimal task-specific fine-tuning.



中文翻译:

TURL:通过表示学习了解表格:ACM SIGMOD 记录:第 51 卷,第 1 期

Web 上的关系表存储了大量的知识。由于此类表格的丰富性,表格理解领域的各种任务都取得了巨大进展。然而,现有的工作通常依赖于高度工程化的特定任务特征和模型架构。在本文中,我们介绍了 TURL,这是一种将预训练/微调范式引入关系 Web 表的新颖框架。在预训练期间,我们的框架以自我监督的方式学习关系表上的深度上下文表示。其具有预训练表示的通用模型设计可以应用于广泛的任务,只需最少的任务特定微调。

更新日期:2022-06-02
down
wechat
bug