Advanced search
1 file | 118.73 KB Add to list
Author
Organization
Abstract
This paper presents a machine learning approach to the resolution of coreferential relations between nominal constituents in Dutch. It is the first significant automatic approach to the resolution of coreferential relations between nominal constituents for this language. The corpusbased strategy was enabled by the annotation of a substantial corpus (ca. 12,500 noun phrases) of Dutch news magazine text with coreferential links for pronominal, proper noun and common noun coreferences. Based on the hypothesis that different types of information sources contribute to a correct resolution of different types of coreferential links, we propose a modular approach in which a separate module is trained per NP type.

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 118.73 KB

Citation

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

MLA
Hoste, Veronique, and Walter Daelemans. “Learning Dutch Coreference Resolution.” Proceedings of the Fifteenth Computational Linguistics in the Netherlands Meeting (CLIN 2004). 2005. 133–148. Print.
APA
Hoste, Veronique, & Daelemans, W. (2005). Learning Dutch coreference resolution. Proceedings of the fifteenth computational linguistics in the Netherlands meeting (CLIN 2004) (pp. 133–148). Presented at the 15th Meeting on Computational Linguistics in the Netherlands (CLIN-15).
Chicago author-date
Hoste, Veronique, and Walter Daelemans. 2005. “Learning Dutch Coreference Resolution.” In Proceedings of the Fifteenth Computational Linguistics in the Netherlands Meeting (CLIN 2004), 133–148.
Chicago author-date (all authors)
Hoste, Veronique, and Walter Daelemans. 2005. “Learning Dutch Coreference Resolution.” In Proceedings of the Fifteenth Computational Linguistics in the Netherlands Meeting (CLIN 2004), 133–148.
Vancouver
1.
Hoste V, Daelemans W. Learning Dutch coreference resolution. Proceedings of the fifteenth computational linguistics in the Netherlands meeting (CLIN 2004). 2005. p. 133–48.
IEEE
[1]
V. Hoste and W. Daelemans, “Learning Dutch coreference resolution,” in Proceedings of the fifteenth computational linguistics in the Netherlands meeting (CLIN 2004), Leiden, The Netherlands, 2005, pp. 133–148.
@inproceedings{598153,
  abstract     = {This paper presents a machine learning approach to the resolution of coreferential relations between nominal constituents in Dutch. It is the first significant automatic approach to the resolution of coreferential relations between nominal constituents for this language. The corpusbased strategy was enabled by the annotation of a substantial corpus (ca. 12,500 noun phrases) of Dutch news magazine text with coreferential links for pronominal, proper noun and common noun coreferences. Based on the hypothesis that different types of information sources contribute to a correct resolution of different types of coreferential links, we propose a modular approach in which a separate module is trained per NP type.},
  author       = {Hoste, Veronique and Daelemans, Walter},
  booktitle    = {Proceedings of the fifteenth computational linguistics in the Netherlands meeting (CLIN 2004)},
  language     = {eng},
  location     = {Leiden, The Netherlands},
  pages        = {133--148},
  title        = {Learning Dutch coreference resolution},
  year         = {2005},
}