Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 512.54 KB
Add to list
  1. Search results
  2. Modeling syntactic dependencies in so...

Modeling syntactic dependencies in southern Dutch dialects

Loic De Langhe (UGent) , Jasper Degraeuwe (UGent) , Melissa Farasyn (UGent) and Veronique Hoste (UGent)
(2025) PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025. p.24-35
Author
Organization
Abstract
Dependency parsing of non-normative language varieties remains a challenge for modern NLP. While contemporary parsers excel at standardized languages, dialectal variation – especially in function words, conjunctives, and verb clustering – introduces syntactic ambiguity that disrupts traditional parsing approaches. In this paper, we conduct a quantitative evaluation of syntactic dependencies in Southern Dutch dialects, leveraging a standardized dialect corpus to isolate syntactic effects from lexical variation. Using a neural biaffine dependency parser with various mono- and multilingual transformer-based encoders, we benchmark parsing performance on standard Dutch, dialectal data, and mixed training sets. Our results demonstrate that incorporating dialect-specific data significantly enhances parsing accuracy, yet certain syntactic structures remain difficult to resolve, even with dedicated adaptation. These findings highlight the need for more nuanced parsing strategies and improved syntactic modeling for non-normative language varieties.

Downloads

  • Download
    2025.depling-1.3.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 512.54 KB

Citation

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

MLA
De Langhe, Loic, et al. “Modeling Syntactic Dependencies in Southern Dutch Dialects.” PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025, edited by Eva Hajičová and Sylvain Kahane, Association for Computational Linguistics (ACL), 2025, pp. 24–35.
APA
De Langhe, L., Degraeuwe, J., Farasyn, M., & Hoste, V. (2025). Modeling syntactic dependencies in southern Dutch dialects. In E. Hajičová & S. Kahane (Eds.), PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025 (pp. 24–35). Association for Computational Linguistics (ACL).
Chicago author-date
De Langhe, Loic, Jasper Degraeuwe, Melissa Farasyn, and Veronique Hoste. 2025. “Modeling Syntactic Dependencies in Southern Dutch Dialects.” In PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025, edited by Eva Hajičová and Sylvain Kahane, 24–35. Association for Computational Linguistics (ACL).
Chicago author-date (all authors)
De Langhe, Loic, Jasper Degraeuwe, Melissa Farasyn, and Veronique Hoste. 2025. “Modeling Syntactic Dependencies in Southern Dutch Dialects.” In PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025, ed by. Eva Hajičová and Sylvain Kahane, 24–35. Association for Computational Linguistics (ACL).
Vancouver
1.
De Langhe L, Degraeuwe J, Farasyn M, Hoste V. Modeling syntactic dependencies in southern Dutch dialects. In: Hajičová E, Kahane S, editors. PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025. Association for Computational Linguistics (ACL); 2025. p. 24–35.
IEEE
[1]
L. De Langhe, J. Degraeuwe, M. Farasyn, and V. Hoste, “Modeling syntactic dependencies in southern Dutch dialects,” in PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025, Ljubljana, Slovenia, 2025, pp. 24–35.
@inproceedings{01K99FCTQ2DXGN9HCNQ1AWX06X,
  abstract     = {{Dependency parsing of non-normative language varieties remains a challenge for modern NLP. While contemporary parsers excel at standardized languages, dialectal variation – especially in function words, conjunctives, and verb clustering – introduces syntactic ambiguity that disrupts traditional parsing approaches. In this paper, we conduct a quantitative evaluation of syntactic dependencies in Southern Dutch dialects, leveraging a standardized dialect corpus to isolate syntactic effects from lexical variation. Using a neural biaffine dependency parser with various mono- and multilingual transformer-based encoders, we benchmark parsing performance on standard Dutch, dialectal data, and mixed training sets. Our results demonstrate that incorporating dialect-specific data significantly enhances parsing accuracy, yet certain syntactic structures remain difficult to resolve, even with dedicated adaptation. These findings highlight the need for more nuanced parsing strategies and improved syntactic modeling for non-normative language varieties.}},
  author       = {{De Langhe, Loic and Degraeuwe, Jasper and Farasyn, Melissa and Hoste, Veronique}},
  booktitle    = {{PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON DEPENDENCY LINGUISTICS, DEPLING, SYNTAXFEST 2025}},
  editor       = {{Hajičová, Eva and Kahane, Sylvain}},
  isbn         = {{9798891762909}},
  language     = {{eng}},
  location     = {{Ljubljana, Slovenia}},
  pages        = {{24--35}},
  publisher    = {{Association for Computational Linguistics (ACL)}},
  title        = {{Modeling syntactic dependencies in southern Dutch dialects}},
  url          = {{https://aclanthology.org/2025.depling-1.3/}},
  year         = {{2025}},
}
Web of Science
Times cited: