@inproceedings{farzam-etal-2024-multi,
title = "Multi-Task Learning Improves Performance in Deep Argument Mining Models",
author = "Farzam, Amirhossein and
Shekhar, Shashank and
Mehlhaff, Isaac and
Morucci, Marco",
editor = "Ajjour, Yamen and
Bar-Haim, Roy and
El Baff, Roxanne and
Liu, Zhexiong and
Skitalinskaya, Gabriella",
booktitle = "Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.argmining-1.5",
pages = "46--58",
abstract = "The successful analysis of argumentative techniques in user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools use state-of-the-art deep learning methods to extract and annotate argumentative techniques from various online text corpora, but each task is treated as separate and different bespoke models are fine-tuned for each dataset. We show that different argument mining tasks share common semantic and logical structure by implementing a multi-task approach to argument mining that meets or exceeds performance from existing methods for the same problems. Our model builds a shared representation of the input and exploits similarities between tasks in order to further boost performance via parameter-sharing. Our results are important for argument mining as they show that different tasks share substantial similarities and suggest a holistic approach to the extraction of argumentative techniques from text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="farzam-etal-2024-multi">
<titleInfo>
<title>Multi-Task Learning Improves Performance in Deep Argument Mining Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amirhossein</namePart>
<namePart type="family">Farzam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Shekhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Mehlhaff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Morucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yamen</namePart>
<namePart type="family">Ajjour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roy</namePart>
<namePart type="family">Bar-Haim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roxanne</namePart>
<namePart type="family">El Baff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhexiong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Skitalinskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The successful analysis of argumentative techniques in user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools use state-of-the-art deep learning methods to extract and annotate argumentative techniques from various online text corpora, but each task is treated as separate and different bespoke models are fine-tuned for each dataset. We show that different argument mining tasks share common semantic and logical structure by implementing a multi-task approach to argument mining that meets or exceeds performance from existing methods for the same problems. Our model builds a shared representation of the input and exploits similarities between tasks in order to further boost performance via parameter-sharing. Our results are important for argument mining as they show that different tasks share substantial similarities and suggest a holistic approach to the extraction of argumentative techniques from text.</abstract>
<identifier type="citekey">farzam-etal-2024-multi</identifier>
<location>
<url>https://aclanthology.org/2024.argmining-1.5</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>46</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Task Learning Improves Performance in Deep Argument Mining Models
%A Farzam, Amirhossein
%A Shekhar, Shashank
%A Mehlhaff, Isaac
%A Morucci, Marco
%Y Ajjour, Yamen
%Y Bar-Haim, Roy
%Y El Baff, Roxanne
%Y Liu, Zhexiong
%Y Skitalinskaya, Gabriella
%S Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F farzam-etal-2024-multi
%X The successful analysis of argumentative techniques in user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools use state-of-the-art deep learning methods to extract and annotate argumentative techniques from various online text corpora, but each task is treated as separate and different bespoke models are fine-tuned for each dataset. We show that different argument mining tasks share common semantic and logical structure by implementing a multi-task approach to argument mining that meets or exceeds performance from existing methods for the same problems. Our model builds a shared representation of the input and exploits similarities between tasks in order to further boost performance via parameter-sharing. Our results are important for argument mining as they show that different tasks share substantial similarities and suggest a holistic approach to the extraction of argumentative techniques from text.
%U https://aclanthology.org/2024.argmining-1.5
%P 46-58
Markdown (Informal)
[Multi-Task Learning Improves Performance in Deep Argument Mining Models](https://aclanthology.org/2024.argmining-1.5) (Farzam et al., ArgMining 2024)
ACL