Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 746.48 KB
Add to list
  1. Search results
  2. A benchmark for dutch end-to-end cros...

A benchmark for dutch end-to-end cross-document event coreference resolution

Loic De Langhe (UGent) , Thierry Desot (UGent) , Orphée De Clercq (UGent) and Veronique Hoste (UGent)
(2023) ELECTRONICS. 12(4).
Author
Organization
Project
Abstract
In this paper, we present a benchmark result for end-to-end cross-document event coreference resolution in Dutch. First, the state of the art of this task in other languages is introduced, as well as currently existing resources and commonly used evaluation metrics. We then build on recently published work to fully explore end-to-end event coreference resolution for the first time in the Dutch language domain. For this purpose, two well-performing transformer-based algorithms for the respective detection and coreference resolution of Dutch textual events are combined in a pipeline architecture and compared to baseline scores relying on feature-based methods. The results are promising and comparable to similar studies in higher-resourced languages; however, they also reveal that in this specific NLP domain, much work remains to be done. In order to gain more insights, an in-depth analysis of the two pipeline components is carried out to highlight and overcome possible shortcoming of the current approach and provide suggestions for future work.
Keywords
event coreference resolution, end-to-end, cross-document, Dutch language domain, NEWS, EXTRACTION

Downloads

  • Download
    electronics-12-00850.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 746.48 KB

Citation

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

MLA
De Langhe, Loic, et al. “A Benchmark for Dutch End-to-End Cross-Document Event Coreference Resolution.” ELECTRONICS, vol. 12, no. 4, 2023, doi:10.3390/electronics12040850.
APA
De Langhe, L., Desot, T., De Clercq, O., & Hoste, V. (2023). A benchmark for dutch end-to-end cross-document event coreference resolution. ELECTRONICS, 12(4). https://doi.org/10.3390/electronics12040850
Chicago author-date
De Langhe, Loic, Thierry Desot, Orphée De Clercq, and Veronique Hoste. 2023. “A Benchmark for Dutch End-to-End Cross-Document Event Coreference Resolution.” ELECTRONICS 12 (4). https://doi.org/10.3390/electronics12040850.
Chicago author-date (all authors)
De Langhe, Loic, Thierry Desot, Orphée De Clercq, and Veronique Hoste. 2023. “A Benchmark for Dutch End-to-End Cross-Document Event Coreference Resolution.” ELECTRONICS 12 (4). doi:10.3390/electronics12040850.
Vancouver
1.
De Langhe L, Desot T, De Clercq O, Hoste V. A benchmark for dutch end-to-end cross-document event coreference resolution. ELECTRONICS. 2023;12(4).
IEEE
[1]
L. De Langhe, T. Desot, O. De Clercq, and V. Hoste, “A benchmark for dutch end-to-end cross-document event coreference resolution,” ELECTRONICS, vol. 12, no. 4, 2023.
@article{01H4110F1NQ0P01WSZSB6ZX71M,
  abstract     = {{In this paper, we present a benchmark result for end-to-end cross-document event coreference resolution in Dutch. First, the state of the art of this task in other languages is introduced, as well as currently existing resources and commonly used evaluation metrics. We then build on recently published work to fully explore end-to-end event coreference resolution for the first time in the Dutch language domain. For this purpose, two well-performing transformer-based algorithms for the respective detection and coreference resolution of Dutch textual events are combined in a pipeline architecture and compared to baseline scores relying on feature-based methods. The results are promising and comparable to similar studies in higher-resourced languages; however, they also reveal that in this specific NLP domain, much work remains to be done. In order to gain more insights, an in-depth analysis of the two pipeline components is carried out to highlight and overcome possible shortcoming of the current approach and provide suggestions for future work.}},
  articleno    = {{850}},
  author       = {{De Langhe, Loic and Desot, Thierry and De Clercq, Orphée and Hoste, Veronique}},
  issn         = {{2079-9292}},
  journal      = {{ELECTRONICS}},
  keywords     = {{event coreference resolution,end-to-end,cross-document,Dutch language domain,NEWS,EXTRACTION}},
  language     = {{eng}},
  number       = {{4}},
  pages        = {{20}},
  title        = {{A benchmark for dutch end-to-end cross-document event coreference resolution}},
  url          = {{http://doi.org/10.3390/electronics12040850}},
  volume       = {{12}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: