An Effective Transition-based Model for Discontinuous NER
This work addresses a specific challenge in biomedical NER where entities are often discontinuous, offering a solution that improves performance in this domain.
The paper tackled the problem of recognizing discontinuous named entities in biomedical texts, which conventional sequence tagging methods cannot handle, and proposed a transition-based model that effectively identifies such mentions without compromising accuracy on continuous ones.
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.