DMNER: Biomedical Entity Recognition by Detection and Matching

TL;DR

DMNER is a versatile biomedical entity recognition framework that improves detection and matching by leveraging external knowledge and various training strategies, demonstrating strong results across multiple datasets.

Contribution

Introduces DMNER, a novel two-step BNER framework that integrates external models and knowledge, enhancing performance in supervised, distantly supervised, and multi-dataset training scenarios.

Findings

Effective in rectifying baseline NER outputs

Achieves satisfactory results in distantly supervised NER

Demonstrates versatility across 10 benchmark datasets

Abstract

Biomedical named entity recognition (BNER) serves as the foundation for numerous biomedical text mining tasks. Unlike general NER, BNER require a comprehensive grasp of the domain, and incorporating external knowledge beyond training data poses a significant challenge. In this study, we propose a novel BNER framework called DMNER. By leveraging existing entity representation models SAPBERT, we tackle BNER as a two-step process: entity boundary detection and biomedical entity matching. DMNER exhibits applicability across multiple NER scenarios: 1) In supervised NER, we observe that DMNER effectively rectifies the output of baseline NER models, thereby further enhancing performance. 2) In distantly supervised NER, combining MRC and AutoNER as span boundary detectors enables DMNER to achieve satisfactory results. 3) For training NER by merging multiple datasets, we adopt a framework similar to DS-NER but additionally leverage ChatGPT to obtain high-quality phrases in the training. Through extensive experiments conducted on 10 benchmark datasets, we demonstrate the versatility and effectiveness of DMNER.