@inproceedings{95d0e3a0afbd43e3a97d67605b79bbf4,
title = "CoVA: Context-aware Visual Attention for Webpage Information Extraction",
abstract = "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 dataset1 of e-commerce websites for which we manually annotate every web element with four labels: product price, product title, product image and others. On this dataset we show that the proposed CoVA approach is a new challenging baseline which improves upon prior state-of-the-art methods.",
author = "Anurendra Kumar and Keval Morabia and Jingjin Wang and Chang, {Kevin Chen Chuan} and Alexander Schwing",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 5th Workshop on e-Commerce and NLP, ECNLP 2022 ; Conference date: 26-05-2022",
year = "2022",
doi = "10.18653/v1/2022.ecnlp-1.11",
language = "English (US)",
series = "ECNLP 2022 - 5th Workshop on e-Commerce and NLP, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "80--90",
editor = "Shervin Malmasi and Oleg Rokhlenko and Nicola Ueffing and Ido Guy and Eugene Agichtein and Surya Kallumadi",
booktitle = "ECNLP 2022 - 5th Workshop on e-Commerce and NLP, Proceedings of the Workshop",
}