@inproceedings{zong-etal-2023-tilfa,
title = "{TILFA}: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining",
author = "Zong, Qing and
Wang, Zhaowei and
Xu, Baixuan and
Zheng, Tianshi and
Shi, Haochen and
Wang, Weiqi and
Song, Yangqiu and
Wong, Ginny and
See, Simon",
editor = "Alshomary, Milad and
Chen, Chung-Chi and
Muresan, Smaranda and
Park, Joonsuk and
Romberg, Julia",
booktitle = "Proceedings of the 10th Workshop on Argument Mining",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.argmining-1.14",
doi = "10.18653/v1/2023.argmining-1.14",
pages = "139--147",
abstract = "A main goal of Argument Mining (AM) is to analyze an author{'}s stance. Unlike previous AM datasets focusing only on text, the shared task at the 10th Workshop on Argument Mining introduces a dataset including both texts and images. Importantly, these images contain both visual elements and optical characters. Our new framework, TILFA (A Unified Framework for Text, Image, and Layout Fusion in Argument Mining), is designed to handle this mixed data. It excels at not only understanding text but also detecting optical characters and recognizing layout details in images. Our model significantly outperforms existing baselines, earning our team, KnowComp, the 1st place in the leaderboard of Argumentative Stance Classification subtask in this shared task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zong-etal-2023-tilfa">
<titleInfo>
<title>TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaowei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baixuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianshi</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haochen</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangqiu</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ginny</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">See</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milad</namePart>
<namePart type="family">Alshomary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonsuk</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Romberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A main goal of Argument Mining (AM) is to analyze an author’s stance. Unlike previous AM datasets focusing only on text, the shared task at the 10th Workshop on Argument Mining introduces a dataset including both texts and images. Importantly, these images contain both visual elements and optical characters. Our new framework, TILFA (A Unified Framework for Text, Image, and Layout Fusion in Argument Mining), is designed to handle this mixed data. It excels at not only understanding text but also detecting optical characters and recognizing layout details in images. Our model significantly outperforms existing baselines, earning our team, KnowComp, the 1st place in the leaderboard of Argumentative Stance Classification subtask in this shared task.</abstract>
<identifier type="citekey">zong-etal-2023-tilfa</identifier>
<identifier type="doi">10.18653/v1/2023.argmining-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.argmining-1.14</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>139</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining
%A Zong, Qing
%A Wang, Zhaowei
%A Xu, Baixuan
%A Zheng, Tianshi
%A Shi, Haochen
%A Wang, Weiqi
%A Song, Yangqiu
%A Wong, Ginny
%A See, Simon
%Y Alshomary, Milad
%Y Chen, Chung-Chi
%Y Muresan, Smaranda
%Y Park, Joonsuk
%Y Romberg, Julia
%S Proceedings of the 10th Workshop on Argument Mining
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zong-etal-2023-tilfa
%X A main goal of Argument Mining (AM) is to analyze an author’s stance. Unlike previous AM datasets focusing only on text, the shared task at the 10th Workshop on Argument Mining introduces a dataset including both texts and images. Importantly, these images contain both visual elements and optical characters. Our new framework, TILFA (A Unified Framework for Text, Image, and Layout Fusion in Argument Mining), is designed to handle this mixed data. It excels at not only understanding text but also detecting optical characters and recognizing layout details in images. Our model significantly outperforms existing baselines, earning our team, KnowComp, the 1st place in the leaderboard of Argumentative Stance Classification subtask in this shared task.
%R 10.18653/v1/2023.argmining-1.14
%U https://aclanthology.org/2023.argmining-1.14
%U https://doi.org/10.18653/v1/2023.argmining-1.14
%P 139-147
Markdown (Informal)
[TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining](https://aclanthology.org/2023.argmining-1.14) (Zong et al., ArgMining-WS 2023)
ACL
- Qing Zong, Zhaowei Wang, Baixuan Xu, Tianshi Zheng, Haochen Shi, Weiqi Wang, Yangqiu Song, Ginny Wong, and Simon See. 2023. TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining. In Proceedings of the 10th Workshop on Argument Mining, pages 139–147, Singapore. Association for Computational Linguistics.