Combining Language and Graph Models for Semi-structured Information Extraction on the Web

TL;DR

GraphScholarBERT is presented, an open-domain information extraction method based on a joint graph and language model structure that can generalize to previously unseen domains without additional data or training and produces only clean extraction results matched to the search keyword.

Abstract

Relation extraction is an efficient way of mining the extraordinary wealth of human knowledge on the Web. Existing methods rely on domain-specific training data or produce noisy outputs. We focus here on extracting targeted relations from semi-structured web pages given only a short description of the relation. We present GraphScholarBERT, an open-domain information extraction method based on a joint graph and language model structure. GraphScholarBERT can generalize to previously unseen domains without additional data or training and produces only clean extraction results matched to the search keyword. Experiments show that GraphScholarBERT can improve extraction F1 scores by as much as 34.8\% compared to previous work in a zero-shot domain and zero-shot website setting.

Figures (2)

• Figure 1: The GraphScholarBERT model architecture
• Figure 2: Graph representation of a webpage. DOM node attributes propagate bi-directionally through the black edges but not the dashed orange edges ("virtual edges"), which are only used for classification.