期刊
INFORMATION SCIENCES
卷 577, 期 -, 页码 49-68出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2021.04.087
关键词
HTML tables; Data extraction
资金
- Fulbright organisation
- University of Seville [TIN2013-40848-R, TIN2016-75394-R, P18-RT-1060, PID2020-112540RB-C44]
- USAF [FA8650-17-C-7715]
The article introduces a new proposal for extracting data from user-friendly HTML tables, which involves pre-processing, functional analysis, and post-processing to achieve data extraction. Experimental results demonstrate the method's superiority in effectiveness and competitiveness in efficiency compared to competitors.
Extracting data from user-friendly HTML tables is difficult because of their different layouts, formats, and encoding problems. In this article, we present a new proposal that first applies several pre-processing heuristics to clean the tables, then performs functional analysis, and finally applies some post-processing heuristics to produce the output. Our most important contribution is regarding functional analysis, which we address by projecting the cells onto a high-dimensional feature space in which a standard clustering technique is used to make the meta-data cells apart from the data cells. We experimented with two large repositories of real-world HTML tables and our results confirm that our proposal can extract data from them with an F-1 score of 89:50% in just 0:09 CPU seconds per table. We confronted our proposal with several competitors and the statistical analysis confirmed its superiority in terms of effectiveness, while it keeps very competitive in terms of efficiency. (C) 2021 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据