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

Abstract

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.

arXiv comment10 pages, 7 figures, to be published in the proceedings of KDD 2021

References in corpus (10)

• Sequence to Sequence Learning with Neural Networks
• Decoupled Weight Decay Regularization
• Semi-Supervised Classification with Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Recurrent Neural Network for Text Classification with Multi-Task Learning
• How Powerful are Graph Neural Networks?
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval
• TableSense: Spreadsheet Table Detection with Convolutional Neural Networks
• Semantic Classification of Tabular Datasets via Character-Level Convolutional Neural Networks

Cited by in corpus (6)

• MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
• Fuzzy Convolution Neural Networks for Tabular Data Classification
• Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
• Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
• Neuron Campaign for Initialization Guided by Information Bottleneck Theory
• Neuron with Steady Response Leads to Better Generalization