@inproceedings{sow-etal-2026-relex,
title = "Relex: A Common Denominator for Connectives and Discourse Relations in {F}rench",
author = "Sow, Fatou and
Toussaint, Yannick and
Constant, Mathieu",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.45/",
pages = "636--648",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sow-etal-2026-relex">
<titleInfo>
<title>Relex: A Common Denominator for Connectives and Discourse Relations in French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatou</namePart>
<namePart type="family">Sow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannick</namePart>
<namePart type="family">Toussaint</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sow-etal-2026-relex</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.45/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>636</start>
<end>648</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Relex: A Common Denominator for Connectives and Discourse Relations in French
%A Sow, Fatou
%A Toussaint, Yannick
%A Constant, Mathieu
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F sow-etal-2026-relex
%X 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.
%U https://aclanthology.org/2026.sigdial-1.45/
%P 636-648
Markdown (Informal)
[Relex: A Common Denominator for Connectives and Discourse Relations in French](https://aclanthology.org/2026.sigdial-1.45/) (Sow et al., SIGDIAL 2026)
ACL