arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.03096cs.LG
收藏

TabularNet:一种理解表格数据语义结构的神经网络结构

TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data

Microsoft Research Asia(微软亚洲研究院);Beijing Normal University(北京师范大学);Peking University(北京大学)

Lun Du, Fei Gao, Xu Chen, Ran Jia, Junshan Wang, Jiang Zhang, Shi Han, Dongmei Zhang

摘要:

由于表格的广泛应用,表格数据无处不在,因此吸引了研究人员的注意力,以提取潜在的信息。表格数据挖掘的关键问题之一是如何自动理解其内在的语义结构。现有的研究通常采用卷积神经网络(CNN)来建模表格结构的空间信息,但忽略了细胞之间更多样化的关系信息,如层次关系和并列关系。为了同时从表中提取空间和关系信息,我们提出了一种新的神经网络架构,TabularNet。TabularNet的空间编码器利用行/列级池化和双向门控递归单元(Bi-GRU)分别捕获统计信息和局部位置相关性。对于关系信息,我们设计了一种新的基于WordNet树的图构造方法,并采用了一种基于图卷积网络(GCN)的编码器,该编码器侧重于单元之间的层次和并列关系。我们的神经网络架构可以是一个统一的神经骨干不同的理解任务,并在多任务的情况下使用。我们用两个真实世界的电子表格数据集对三个分类任务进行了广泛的实验,结果证明了我们提出的TabularNet在最先进的基线上的有效性。

英文摘要:

Tabular data are ubiquitous for the widespread applications of tables and hence have attracted the attention of researchers to extract underlying information. One of the critical problems in mining tabular data is how to understand their inherent semantic structures automatically. Existing studies typically adopt Convolutional Neural Network (CNN) to model the spatial information of tabular structures yet ignore more diverse relational information between cells, such as the hierarchical and paratactic relationships. To simultaneously extract spatial and relational information from tables, we propose a novel neural network architecture, TabularNet. The spatial encoder of TabularNet utilizes the row/column-level Pooling and the Bidirectional Gated Recurrent Unit (Bi-GRU) to capture statistical information and local positional correlation, respectively. For relational information, we design a new graph construction method based on the WordNet tree and adopt a Graph Convolutional Network (GCN) based encoder that focuses on the hierarchical and paratactic relationships between cells. Our neural network architecture can be a unified neural backbone for different understanding tasks and utilized in a multitask scenario. We conduct extensive experiments on three classification tasks with two real-world spreadsheet data sets, and the results demonstrate the effectiveness of our proposed TabularNet over state-of-the-art baselines.

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。

↑