Entity Linking in Web Tables with Multiple Linked Knowledge Bases

Abstract

The World-Wide Web contains a large scale of valuable relational data, which are embedded in HTML tables (i.e. Web tables). To extract machine-readable knowledge from Web tables, some work tries to annotate the contents of Web tables as RDF triples. One critical step of the annotation is entity linking (EL), which aims to map the string mentions in table cells to their referent entities in a knowledge base (KB). In this paper, we present a new approach for EL in Web tables. Different from previous work, the proposed approach replaces a single KB with multiple linked KBs as the sources of entities to improve the quality of EL. In our approach, we first apply a general graph-based algorithm to EL in Web tables with each single KB. Then, we leverage the existing and newly learned “sameAs” relations between the entities from different KBs to help improve the results of EL in the first step. We conduct experiments on the sampled Web tables with Zhishi.me, which consists of three linked encyclopedic KBs. The experimental results show that our approach outperforms the state-of-the-art table’s EL methods in different evaluation metrics.