@inproceedings{costa-kosseim-2025-multi,
title = "Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning",
author = "Costa, Nelson Filipe and
Kosseim, Leila",
editor = "B{\'e}chet, Fr{\'e}d{\'e}ric and
Lef{\`e}vre, Fabrice and
Asher, Nicholas and
Kim, Seokhwan and
Merlin, Teva",
booktitle = "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2025",
address = "Avignon, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sigdial-1.4/",
pages = "48--61",
abstract = "This paper introduces the first multi-lingual and multi-label classification model for implicit discourse relation recognition (IDRR). Our model, HArch, is evaluated on the recently released DiscoGeM 2.0 corpus and leverages hierarchical dependencies between discourse senses to predict probability distributions across all three sense levels in the PDTB 3.0 framework. We compare several pre-trained encoder backbones and find that RoBERTa-HArch achieves the best performance in English, while XLM-RoBERTa-HArch performs best in the multi-lingual setting. In addition, we compare our fine-tuned models against GPT-4o and Llama-4-Maverick using few-shot prompting across all language configurations. Our results show that our fine-tuned models consistently outperform these LLMs, highlighting the advantages of task-specific fine-tuning over prompting in IDRR. Finally, we report SOTA results on the DiscoGeM 1.0 corpus, further validating the effectiveness of our hierarchical approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="costa-kosseim-2025-multi">
<titleInfo>
<title>Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="given">Filipe</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leila</namePart>
<namePart type="family">Kosseim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrice</namePart>
<namePart type="family">Lefèvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Asher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teva</namePart>
<namePart type="family">Merlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Avignon, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces the first multi-lingual and multi-label classification model for implicit discourse relation recognition (IDRR). Our model, HArch, is evaluated on the recently released DiscoGeM 2.0 corpus and leverages hierarchical dependencies between discourse senses to predict probability distributions across all three sense levels in the PDTB 3.0 framework. We compare several pre-trained encoder backbones and find that RoBERTa-HArch achieves the best performance in English, while XLM-RoBERTa-HArch performs best in the multi-lingual setting. In addition, we compare our fine-tuned models against GPT-4o and Llama-4-Maverick using few-shot prompting across all language configurations. Our results show that our fine-tuned models consistently outperform these LLMs, highlighting the advantages of task-specific fine-tuning over prompting in IDRR. Finally, we report SOTA results on the DiscoGeM 1.0 corpus, further validating the effectiveness of our hierarchical approach.</abstract>
<identifier type="citekey">costa-kosseim-2025-multi</identifier>
<location>
<url>https://aclanthology.org/2025.sigdial-1.4/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>48</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning
%A Costa, Nelson Filipe
%A Kosseim, Leila
%Y Béchet, Frédéric
%Y Lefèvre, Fabrice
%Y Asher, Nicholas
%Y Kim, Seokhwan
%Y Merlin, Teva
%S Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2025
%8 August
%I Association for Computational Linguistics
%C Avignon, France
%F costa-kosseim-2025-multi
%X This paper introduces the first multi-lingual and multi-label classification model for implicit discourse relation recognition (IDRR). Our model, HArch, is evaluated on the recently released DiscoGeM 2.0 corpus and leverages hierarchical dependencies between discourse senses to predict probability distributions across all three sense levels in the PDTB 3.0 framework. We compare several pre-trained encoder backbones and find that RoBERTa-HArch achieves the best performance in English, while XLM-RoBERTa-HArch performs best in the multi-lingual setting. In addition, we compare our fine-tuned models against GPT-4o and Llama-4-Maverick using few-shot prompting across all language configurations. Our results show that our fine-tuned models consistently outperform these LLMs, highlighting the advantages of task-specific fine-tuning over prompting in IDRR. Finally, we report SOTA results on the DiscoGeM 1.0 corpus, further validating the effectiveness of our hierarchical approach.
%U https://aclanthology.org/2025.sigdial-1.4/
%P 48-61
Markdown (Informal)
[Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning](https://aclanthology.org/2025.sigdial-1.4/) (Costa & Kosseim, SIGDIAL 2025)
ACL