An Effective Transition-based Model for Discontinuous NER

TL;DR

This paper introduces a transition-based neural model for biomedical NER that effectively recognizes discontinuous mentions, overcoming limitations of traditional sequence tagging methods.

Contribution

The paper presents a novel transition-based approach with neural encoding specifically designed for discontinuous NER in biomedical texts.

Findings

Effective recognition of discontinuous mentions in biomedical datasets

Maintains accuracy on continuous mentions

Outperforms traditional sequence tagging methods

Abstract

Unlike widely used Named Entity Recognition (NER) data sets in generic domains, biomedical NER data sets often contain mentions consisting of discontinuous spans. Conventional sequence tagging techniques encode Markov assumptions that are efficient but preclude recovery of these mentions. We propose a simple, effective transition-based model with generic neural encoding for discontinuous NER. Through extensive experiments on three biomedical data sets, we show that our model can effectively recognize discontinuous mentions without sacrificing the accuracy on continuous mentions.