Web Data Extraction Based on Tag Path Clustering

Abstract

Fully automatic methods that extract structured data from the Web have been studied extensively. The existing methods suffice for simple extraction, but they often fail to handle more complicated Web pages. This paper introduces a method based on tag path clustering to extract structured data. The method gets complete tag path collection by parsing the DOM tree of the Web document. Clustering of tag paths is performed based on introduced similarity measure and the data area can be targeted, then taking advantage of features of tag position, we can separate and filter record, finally complete data extraction. Experiments show this method achieves higher accuracy than previous methods.

CoVA: Context-aware Visual Attention for Webpage Information Extraction

“…Separately, attention has been used for contextual learning in OD (Li et al, 2013;Hsieh et al, 2019;Morabia et al, 2020) and image captioning (You et al, 2016). Attention mechanisms have also been employed over graphs to learn an optimal representation of nodes while taking graph structure into account (Veličković et al, 2017).…”

CoVA: Context-aware Visual Attention for Webpage Information Extraction

“…Luo et al [34] use attention over a BiLSTM-CRF layer for Named Entity Recognition (NER) on biomedical data. Separately, attention has been used for contextual learning in OD [20,26,37] and image captioning [56]. Attention mechanisms have also been employed over graphs to learn an optimal representation of nodes while taking graph structure into account [52].…”