Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking

TL;DR

BLINKout is a novel BERT-based entity linking method that effectively identifies out-of-KB mentions, enhancing knowledge base maintenance across multiple domains and datasets.

Contribution

It introduces new techniques for NIL entity representation and classification, along with dataset construction strategies for out-of-KB mention detection.

Findings

BLINKout outperforms existing methods in identifying out-of-KB mentions.

Effective across diverse datasets including clinical, biomedical, and Wikipedia.

Improves KB maintenance by accurately detecting mentions lacking KB entities.

Abstract

Discovering entity mentions that are out of a Knowledge Base (KB) from texts plays a critical role in KB maintenance, but has not yet been fully explored. The current methods are mostly limited to the simple threshold-based approach and feature-based classification, and the datasets for evaluation are relatively rare. We propose BLINKout, a new BERT-based Entity Linking (EL) method which can identify mentions that do not have corresponding KB entities by matching them to a special NIL entity. To better utilize BERT, we propose new techniques including NIL entity representation and classification, with synonym enhancement. We also apply KB Pruning and Versioning strategies to automatically construct out-of-KB datasets from common in-KB EL datasets. Results on five datasets of clinical notes, biomedical publications, and Wikipedia articles in various domains show the advantages of BLINKout over existing methods to identify out-of-KB mentions for the medical ontologies, UMLS, SNOMED CT, and the general KB, WikiData.