Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.56 MB
Add to list
  1. Search results
  2. Position-aware end-to-end cross-docum...

Position-aware end-to-end cross-document event coreference resolution for Dutch

Loic De Langhe (UGent) , Orphée De Clercq (UGent) and Veronique Hoste (UGent)
(2025) NATURAL LANGUAGE PROCESSING. 13.
Author
Organization
Project
Abstract
Natural language understanding entails the ability to comprehend the relations between various people, objects or events throughout one, or multiple, text(s). Event coreference resolution (ECR) is a discourse-based natural language processing (NLP) task which aims to link those textual events, be they real or fictional, that refer to the same conceptual event. In this paper, we introduce a novel end-to-end approach for cross-document ECR which combines expert-level positional knowledge and graph-based representations in order to create a memory-efficient and accurate system meant for the detection and resolution of events in large document collections. We make three fundamental architectural changes to a current state-of-the-art cross-document ECR system and show that our approach outperforms this earlier model (+ 4% CONLL F1) on a large Dutch ECR dataset. Moreover, we show through in-depth qualitative and quantitative analysis that our proposed approach consistently detects more relevant events and suffers notably less from the typical issues models exhibit when predicting coreference chains.
Keywords
Coreference Resolution, Discourse Processing, Events

Downloads

  • Download
    publisher version.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.56 MB

Citation

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

MLA
De Langhe, Loic, et al. “Position-Aware End-to-End Cross-Document Event Coreference Resolution for Dutch.” NATURAL LANGUAGE PROCESSING, vol. 13, 2025, doi:10.1016/j.nlp.2025.100184.
APA
De Langhe, L., De Clercq, O., & Hoste, V. (2025). Position-aware end-to-end cross-document event coreference resolution for Dutch. NATURAL LANGUAGE PROCESSING, 13. https://doi.org/10.1016/j.nlp.2025.100184
Chicago author-date
De Langhe, Loic, Orphée De Clercq, and Veronique Hoste. 2025. “Position-Aware End-to-End Cross-Document Event Coreference Resolution for Dutch.” NATURAL LANGUAGE PROCESSING 13. https://doi.org/10.1016/j.nlp.2025.100184.
Chicago author-date (all authors)
De Langhe, Loic, Orphée De Clercq, and Veronique Hoste. 2025. “Position-Aware End-to-End Cross-Document Event Coreference Resolution for Dutch.” NATURAL LANGUAGE PROCESSING 13. doi:10.1016/j.nlp.2025.100184.
Vancouver
1.
De Langhe L, De Clercq O, Hoste V. Position-aware end-to-end cross-document event coreference resolution for Dutch. NATURAL LANGUAGE PROCESSING. 2025;13.
IEEE
[1]
L. De Langhe, O. De Clercq, and V. Hoste, “Position-aware end-to-end cross-document event coreference resolution for Dutch,” NATURAL LANGUAGE PROCESSING, vol. 13, 2025.
@article{01K99FR2Y35A4E9D816RH9FE35,
  abstract     = {{Natural language understanding entails the ability to comprehend the relations between various people, objects or events throughout one, or multiple, text(s). Event coreference resolution (ECR) is a discourse-based natural language processing (NLP) task which aims to link those textual events, be they real or fictional, that refer to the same conceptual event. In this paper, we introduce a novel end-to-end approach for cross-document ECR which combines expert-level positional knowledge and graph-based representations in order to create a memory-efficient and accurate system meant for the detection and resolution of events in large document collections. We make three fundamental architectural changes to a current state-of-the-art cross-document ECR system and show that our approach outperforms this earlier model (+ 4% CONLL F1) on a large Dutch ECR dataset. Moreover, we show through in-depth qualitative and quantitative analysis that our proposed approach consistently detects more relevant events and suffers notably less from the typical issues models exhibit when predicting coreference chains.}},
  articleno    = {{100184}},
  author       = {{De Langhe, Loic and De Clercq, Orphée and Hoste, Veronique}},
  issn         = {{2977-0424}},
  journal      = {{NATURAL LANGUAGE PROCESSING}},
  keywords     = {{Coreference Resolution,Discourse Processing,Events}},
  language     = {{eng}},
  pages        = {{17}},
  title        = {{Position-aware end-to-end cross-document event coreference resolution for Dutch}},
  url          = {{http://doi.org/10.1016/j.nlp.2025.100184}},
  volume       = {{13}},
  year         = {{2025}},
}
Altmetric
View in Altmetric