Nested Named Entity Recognition as Single-Pass Sequence Labeling

Alberto Muñoz-Ortiz, David Vilares, Caio Corro, Carlos Gómez-Rodríguez


Abstract
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.
Anthology ID:
2025.findings-emnlp.530
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9993–10002
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.530/
DOI:
Bibkey:
Cite (ACL):
Alberto Muñoz-Ortiz, David Vilares, Caio Corro, and Carlos Gómez-Rodríguez. 2025. Nested Named Entity Recognition as Single-Pass Sequence Labeling. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9993–10002, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Nested Named Entity Recognition as Single-Pass Sequence Labeling (Muñoz-Ortiz et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.530.pdf
Checklist:
 2025.findings-emnlp.530.checklist.pdf