@inproceedings{ruby-etal-2025-multimodal,
title = "Multimodal Extraction and Recognition of {A}rabic Implicit Discourse Relations",
author = "Ruby, Ahmed and
Hardmeier, Christian and
Stymne, Sara",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.363/",
pages = "5415--5429",
abstract = "Most research on implicit discourse relation identification has focused on written language, however, it is also crucial to understand these relations in spoken discourse. We introduce a novel method for implicit discourse relation identification across both text and speech, that allows us to extract examples of semantically equivalent pairs of implicit and explicit discourse markers, based on aligning speech+transcripts with subtitles in another language variant. We apply our method to Egyptian Arabic, resulting in a novel high-quality dataset of spoken implicit discourse relations. We present a comprehensive approach to modeling implicit discourse relation classification using audio and text data with a range of different models. We find that text-based models outperform audio-based models, but combining text and audio features can lead to enhanced performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruby-etal-2025-multimodal">
<titleInfo>
<title>Multimodal Extraction and Recognition of Arabic Implicit Discourse Relations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ruby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most research on implicit discourse relation identification has focused on written language, however, it is also crucial to understand these relations in spoken discourse. We introduce a novel method for implicit discourse relation identification across both text and speech, that allows us to extract examples of semantically equivalent pairs of implicit and explicit discourse markers, based on aligning speech+transcripts with subtitles in another language variant. We apply our method to Egyptian Arabic, resulting in a novel high-quality dataset of spoken implicit discourse relations. We present a comprehensive approach to modeling implicit discourse relation classification using audio and text data with a range of different models. We find that text-based models outperform audio-based models, but combining text and audio features can lead to enhanced performance.</abstract>
<identifier type="citekey">ruby-etal-2025-multimodal</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.363/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5415</start>
<end>5429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Extraction and Recognition of Arabic Implicit Discourse Relations
%A Ruby, Ahmed
%A Hardmeier, Christian
%A Stymne, Sara
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ruby-etal-2025-multimodal
%X Most research on implicit discourse relation identification has focused on written language, however, it is also crucial to understand these relations in spoken discourse. We introduce a novel method for implicit discourse relation identification across both text and speech, that allows us to extract examples of semantically equivalent pairs of implicit and explicit discourse markers, based on aligning speech+transcripts with subtitles in another language variant. We apply our method to Egyptian Arabic, resulting in a novel high-quality dataset of spoken implicit discourse relations. We present a comprehensive approach to modeling implicit discourse relation classification using audio and text data with a range of different models. We find that text-based models outperform audio-based models, but combining text and audio features can lead to enhanced performance.
%U https://aclanthology.org/2025.coling-main.363/
%P 5415-5429
Markdown (Informal)
[Multimodal Extraction and Recognition of Arabic Implicit Discourse Relations](https://aclanthology.org/2025.coling-main.363/) (Ruby et al., COLING 2025)
ACL