Nested Named Entity Recognition as Single-Pass Sequence Labeling
This addresses nested entity recognition for NLP applications, but it is incremental as it builds on prior linearization methods.
The paper tackles nested named entity recognition by casting it as a single-pass sequence labeling task, achieving competitive performance with efficient training using off-the-shelf libraries.
We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to straightforward token classification. By combining these constituency linearizations with pretrained encoders, our method captures nested entities while performing exactly n tagging actions. Our approach achieves competitive performance compared to less efficient systems, and it can be trained using any off-the-shelf sequence labeling library.