CoVA: Context-aware Visual Attention for Webpage Information Extraction
This addresses webpage information extraction for knowledge base creation, offering an incremental improvement over existing methods.
The paper tackles webpage information extraction by reformulating it as a context-aware object detection task, proposing CoVA, which combines visual and DOM features, and shows it improves upon prior state-of-the-art methods on a new e-commerce dataset.
Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as context and appearance are encoded in an abstract manner. To address this challenge we propose to reformulate WIE as a context-aware Webpage Object Detection task. Specifically, we develop a Context-aware Visual Attention-based (CoVA) detection pipeline which combines appearance features with syntactical structure from the DOM tree. To study the approach we collect a new large-scale dataset of e-commerce websites for which we manually annotate every web element with four labels: product price, product title, product image and background. On this dataset we show that the proposed CoVA approach is a new challenging baseline which improves upon prior state-of-the-art methods.