Proceedings of the Third Workshop on Scientific Document Understanding at AAAI-2023

A Practical Entity Linking System for Tables in Scientific Literature

Varish Mulwad, Tim Finin, Vijay S. Kumar, Jenny Weisenberg Williams, Sharad Dixit, and Anupam Joshi

February 14, 2023

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 to link domain-specific entities, especially those embedded within tables in COVID-19-related scientific literature. We describe the setup of an efficient offline instance of the system, making our entity-linking approach more feasible in practice. As part of a broader approach to inferring the semantic meaning of scientific tables, we leverage their structural and semantic characteristics to improve overall entity-linking performance.

BibTeX OWL Tweet Scholar

Tags: ai, covid, embedding, entity linking, knowledge graph, tables, vector, wikidata

Type: InProceedings

Publisher: CEUR Workshop Proceedings

Volume: Vol-3656

Note:

Downloads: 1810 downloads