Find the Funding: Entity Linking with Incomplete Funding Knowledge Bases

TL;DR

This paper introduces a transformer-based entity linking model tailored for funding information extraction from academic articles, effectively handling incomplete knowledge bases and missing entities, thereby improving accuracy over existing methods.

Contribution

The authors develop a novel entity linking approach that predicts NIL for missing entities and addresses data scarcity, outperforming current baselines in funding information extraction.

Findings

Model outperforms existing baselines in funding entity linking

Effectively predicts NIL for missing entities in KB

Handles data scarcity efficiently

Abstract

Automatic extraction of funding information from academic articles adds significant value to industry and research communities, such as tracking research outcomes by funding organizations, profiling researchers and universities based on the received funding, and supporting open access policies. Two major challenges of identifying and linking funding entities are: (i) sparse graph structure of the Knowledge Base (KB), which makes the commonly used graph-based entity linking approaches suboptimal for the funding domain, (ii) missing entities in KB, which (unlike recent zero-shot approaches) requires marking entity mentions without KB entries as NIL. We propose an entity linking model that can perform NIL prediction and overcome data scarcity issues in a time and data-efficient manner. Our model builds on a transformer-based mention detection and bi-encoder model to perform entity linking. We show that our model outperforms strong existing baselines.