A Practical Entity Linking System for Tables in Scientific Literature
This work addresses entity linking for scientific tables to aid knowledge graph construction, but it appears incremental as it adapts an existing general-purpose system.
The paper tackles the problem of linking entities in tables from scientific literature to Wikidata, specifically adapting the system for COVID-19-related documents, and leverages table structure and semantics to improve performance, though no concrete numbers are provided.
Entity linking is an important step towards constructing knowledge graphs that facilitate advanced question answering over scientific documents, including the retrieval of relevant information included in tables within these documents. This paper introduces a general-purpose system for linking entities to items in the Wikidata knowledge base. It describes how we adapt this system for linking domain-specific entities, especially for those entities embedded within tables drawn from COVID-19-related scientific literature. We describe the setup of an efficient offline instance of the system that enables our entity-linking approach to be more feasible in practice. As part of a broader approach to infer the semantic meaning of scientific tables, we leverage the structural and semantic characteristics of the tables to improve overall entity linking performance.