Relex: A Common Denominator for Connectives and Discourse Relations in French

Fatou Sow, Yannick Toussaint, Mathieu Constant


Abstract
The lack of sufficiently large French resources linking discourse connectives to the relations they express in context hinders the training of models that map connectives to their discourse relations. We address this gap by introducing two complementary datasets: a large-scale, semi-automatically annotated corpus and a manually validated dataset. Both resources annotate connectives and their discourse relations according to the French lexicon LEXCONN. Relying on the large-scale corpus, we train Relex, a CamemBERT-based model fine-tuned to predict, among 19 relation types, the relation expressed by a connective. Despite being trained on a fixed inventory of connectives, Relex extends to previously unseen connectives and achieves an F1 score of 0.59.
Anthology ID:
2026.sigdial-1.45
Volume:
Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
August
Year:
2026
Address:
Atlanta, Georgia, USA
Editors:
Jinho D. Choi, Yun-Nung Chen, Kotaro Funakoshi, Ali Emami
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
636–648
Language:
URL:
https://aclanthology.org/2026.sigdial-1.45/
DOI:
Bibkey:
Cite (ACL):
Fatou Sow, Yannick Toussaint, and Mathieu Constant. 2026. Relex: A Common Denominator for Connectives and Discourse Relations in French. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 636–648, Atlanta, Georgia, USA. Association for Computational Linguistics.
Cite (Informal):
Relex: A Common Denominator for Connectives and Discourse Relations in French (Sow et al., SIGDIAL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.sigdial-1.45.pdf