Nested Named Entity Recognition as Single-Pass Sequence Labeling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Muñoz-Ortiz, Alberto, Vilares, David, Corro, Caio, Gómez-Rodríguez, Carlos
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911183294955520
author Muñoz-Ortiz, Alberto
Vilares, David
Corro, Caio
Gómez-Rodríguez, Carlos
author_facet Muñoz-Ortiz, Alberto
Vilares, David
Corro, Caio
Gómez-Rodríguez, Carlos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16855
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nested Named Entity Recognition as Single-Pass Sequence Labeling
Muñoz-Ortiz, Alberto
Vilares, David
Corro, Caio
Gómez-Rodríguez, Carlos
Computation and Language
68T50
I.2.7
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.
title Nested Named Entity Recognition as Single-Pass Sequence Labeling
topic Computation and Language
68T50
I.2.7
url https://arxiv.org/abs/2505.16855