@inproceedings{mestre-etal-2021-arg,
title = "{M}-Arg: Multimodal Argument Mining Dataset for Political Debates with Audio and Transcripts",
author = "Mestre, Rafael and
Milicin, Razvan and
Middleton, Stuart E. and
Ryan, Matt and
Zhu, Jiatong and
Norman, Timothy J.",
editor = "Al-Khatib, Khalid and
Hou, Yufang and
Stede, Manfred",
booktitle = "Proceedings of the 8th Workshop on Argument Mining",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.argmining-1.8/",
doi = "10.18653/v1/2021.argmining-1.8",
pages = "78--88",
abstract = "Argumentation mining aims at extracting, analysing and modelling people`s arguments, but large, high-quality annotated datasets are limited, and no multimodal datasets exist for this task. In this paper, we present M-Arg, a multimodal argument mining dataset with a corpus of US 2020 presidential debates, annotated through crowd-sourced annotations. This dataset allows models to be trained to extract arguments from natural dialogue such as debates using information like the intonation and rhythm of the speaker. Our dataset contains 7 hours of annotated US presidential debates, 6527 utterances and 4104 relation labels, and we report results from different baseline models, namely a text-only model, an audio-only model and multimodal models that extract features from both text and audio. With accuracy reaching 0.86 in multimodal models, we find that audio features provide added value with respect to text-only models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mestre-etal-2021-arg">
<titleInfo>
<title>M-Arg: Multimodal Argument Mining Dataset for Political Debates with Audio and Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Mestre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Razvan</namePart>
<namePart type="family">Milicin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stuart</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Middleton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Ryan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiatong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Norman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Al-Khatib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Argumentation mining aims at extracting, analysing and modelling people‘s arguments, but large, high-quality annotated datasets are limited, and no multimodal datasets exist for this task. In this paper, we present M-Arg, a multimodal argument mining dataset with a corpus of US 2020 presidential debates, annotated through crowd-sourced annotations. This dataset allows models to be trained to extract arguments from natural dialogue such as debates using information like the intonation and rhythm of the speaker. Our dataset contains 7 hours of annotated US presidential debates, 6527 utterances and 4104 relation labels, and we report results from different baseline models, namely a text-only model, an audio-only model and multimodal models that extract features from both text and audio. With accuracy reaching 0.86 in multimodal models, we find that audio features provide added value with respect to text-only models.</abstract>
<identifier type="citekey">mestre-etal-2021-arg</identifier>
<identifier type="doi">10.18653/v1/2021.argmining-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.argmining-1.8/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>78</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T M-Arg: Multimodal Argument Mining Dataset for Political Debates with Audio and Transcripts
%A Mestre, Rafael
%A Milicin, Razvan
%A Middleton, Stuart E.
%A Ryan, Matt
%A Zhu, Jiatong
%A Norman, Timothy J.
%Y Al-Khatib, Khalid
%Y Hou, Yufang
%Y Stede, Manfred
%S Proceedings of the 8th Workshop on Argument Mining
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F mestre-etal-2021-arg
%X Argumentation mining aims at extracting, analysing and modelling people‘s arguments, but large, high-quality annotated datasets are limited, and no multimodal datasets exist for this task. In this paper, we present M-Arg, a multimodal argument mining dataset with a corpus of US 2020 presidential debates, annotated through crowd-sourced annotations. This dataset allows models to be trained to extract arguments from natural dialogue such as debates using information like the intonation and rhythm of the speaker. Our dataset contains 7 hours of annotated US presidential debates, 6527 utterances and 4104 relation labels, and we report results from different baseline models, namely a text-only model, an audio-only model and multimodal models that extract features from both text and audio. With accuracy reaching 0.86 in multimodal models, we find that audio features provide added value with respect to text-only models.
%R 10.18653/v1/2021.argmining-1.8
%U https://aclanthology.org/2021.argmining-1.8/
%U https://doi.org/10.18653/v1/2021.argmining-1.8
%P 78-88
Markdown (Informal)
[M-Arg: Multimodal Argument Mining Dataset for Political Debates with Audio and Transcripts](https://aclanthology.org/2021.argmining-1.8/) (Mestre et al., ArgMining 2021)
ACL