Web Table Classification based on Visual Features

TL;DR

This paper introduces a novel web table classification method using visual features extracted from table images via CNNs, achieving high accuracy and surpassing existing HTML-based feature methods.

Contribution

The paper presents a CNN-based approach for web table classification that relies solely on visual appearance, eliminating the need for explicit HTML feature engineering.

Findings

ResNet50 achieves 93.29% F1 score with CNN classification.

Combining visual and explicit features yields 93.70% F-measure.

Proposed method outperforms state-of-the-art HTML feature-based techniques.

Abstract

Tables on the web constitute a valuable data source for many applications, like factual search and knowledge base augmentation. However, as genuine tables containing relational knowledge only account for a small proportion of tables on the web, reliable genuine web table classification is a crucial first step of table extraction. Previous works usually rely on explicit feature construction from the HTML code. In contrast, we propose an approach for web table classification by exploiting the full visual appearance of a table, which works purely by applying a convolutional neural network on the rendered image of the web table. Since these visual features can be extracted automatically, our approach circumvents the need for explicit feature construction. A new hand labeled gold standard dataset containing HTML source code and images for 13,112 tables was generated for this task. Transfer learning techniques are applied to well known VGG16 and ResNet50 architectures. The evaluation of CNN image classification with fine tuned ResNet50 (F1 93.29%) shows that this approach achieves results comparable to previous solutions using explicitly defined HTML code based features. By combining visual and explicit features, an F-measure of 93.70% can be achieved by Random Forest classification, which beats current state of the art methods.