Advanced search
1 file | 383.31 KB

Fine-grained Dutch named entity recognition

Bart Desmet (UGent) and Veronique Hoste (UGent)
Author
Organization
Project
LT3
Abstract
This paper describes the creation of a fine-grained named entity annotation scheme and corpus for Dutch, and experiments on automatic main type and subtype named entity recognition. We give an overview of existing named entity annotation schemes, and motivate our own, which describes six main types (persons, organizations, locations, products, events and miscellaneous named entities) and finer-grained information on subtypes and metonymic usage. This was applied to a one-million-word subset of the Dutch SoNaR reference corpus. The classifier for main type named entities achieves a micro-averaged F-score of 84.91 %, and is publicly available, along with the corpus and annotations.
Keywords
named entity recognition, annotation, classifier ensembles, subtype classification

Downloads

  • LRE Desmet 2014.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 383.31 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Desmet, Bart, and Veronique Hoste. 2014. “Fine-grained Dutch Named Entity Recognition.” Language Resources and Evaluation 48 (2): 307–343.
APA
Desmet, Bart, & Hoste, V. (2014). Fine-grained Dutch named entity recognition. LANGUAGE RESOURCES AND EVALUATION, 48(2), 307–343.
Vancouver
1.
Desmet B, Hoste V. Fine-grained Dutch named entity recognition. LANGUAGE RESOURCES AND EVALUATION. Springer Netherlands; 2014;48(2):307–43.
MLA
Desmet, Bart, and Veronique Hoste. “Fine-grained Dutch Named Entity Recognition.” LANGUAGE RESOURCES AND EVALUATION 48.2 (2014): 307–343. Print.
@article{4246431,
  abstract     = {This paper describes the creation of a fine-grained named entity annotation scheme and corpus for Dutch, and experiments on automatic main type and subtype named entity recognition. We give an overview of existing named entity annotation schemes, and motivate our own, which describes six main types (persons, organizations, locations, products, events and miscellaneous named entities) and finer-grained information on subtypes and metonymic usage. This was applied to a one-million-word subset of the Dutch SoNaR reference corpus. The classifier for main type named entities achieves a micro-averaged F-score of 84.91 \%, and is publicly available, along with the corpus and annotations.},
  author       = {Desmet, Bart and Hoste, Veronique},
  issn         = {1574-020X},
  journal      = {LANGUAGE RESOURCES AND EVALUATION},
  keyword      = {named entity recognition,annotation,classi\unmatched{fb01}er ensembles,subtype classi\unmatched{fb01}cation},
  language     = {eng},
  number       = {2},
  pages        = {307--343},
  publisher    = {Springer Netherlands},
  title        = {Fine-grained Dutch named entity recognition},
  url          = {http://dx.doi.org/10.1007/s10579-013-9255-y},
  volume       = {48},
  year         = {2014},
}

Altmetric
View in Altmetric
Web of Science
Times cited: