A Practical Entity Linking System for Tables in Scientific Literature

TL;DR

This paper presents a practical entity linking system tailored for tables in scientific literature, enhancing knowledge graph construction and question answering by linking domain-specific entities, especially in COVID-19 research.

Contribution

It introduces a versatile entity linking system adapted for scientific tables, with an efficient offline setup and methods leveraging table structure to improve linking accuracy.

Findings

Effective linking of domain-specific entities in scientific tables

Improved entity linking performance using table structure and semantics

Feasible offline system setup for practical applications

Abstract

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.