Neural Entity Recognition with Gazetteer based Fusion

TL;DR

This paper introduces a gazetteer-based fusion approach for clinical NER that enhances robustness, interpretability, and zero-shot adaptability with limited data, outperforming baseline models on multiple datasets.

Contribution

It proposes a novel auxiliary gazetteer fusion model for clinical NER, improving data efficiency, interpretability, and zero-shot recognition of new entities.

Findings

+1.7 micro-F1 on i2b2 with 20% training data

+4.7 micro-F1 on unseen entity mentions

Model adapts quickly to new mentions without re-training

Abstract

Incorporating external knowledge into Named Entity Recognition (NER) systems has been widely studied in the generic domain. In this paper, we focus on clinical domain where only limited data is accessible and interpretability is important. Recent advancement in technology and the acceleration of clinical trials has resulted in the discovery of new drugs, procedures as well as medical conditions. These factors motivate towards building robust zero-shot NER systems which can quickly adapt to new medical terminology. We propose an auxiliary gazetteer model and fuse it with an NER system, which results in better robustness and interpretability across different clinical datasets. Our gazetteer based fusion model is data efficient, achieving +1.7 micro-F1 gains on the i2b2 dataset using 20% training data, and brings + 4.7 micro-F1 gains on novel entity mentions never presented during training. Moreover, our fusion model is able to quickly adapt to new mentions in gazetteers without re-training and the gains from the proposed fusion model are transferable to related datasets.