TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining
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 text and images. Importantly, these images contain both visual elements and optica...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Zong, Qing Wang, Zhaowei Xu, Baixuan Zheng, Tianshi Shi, Haochen Wang, Weiqi Song, Yangqiu Wong, Ginny Y See, Simon |
| description | 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 text 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. |
| doi_str_mv | 10.48550/arxiv.2310.05210 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2310_05210</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2310_05210</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-dbd194d2ef3ac7b30fefb5202bc0c83fe75a1140423cbcb5121bc077b4120dc63</originalsourceid><addsrcrecordid>eNotz8tKw0AYBeDZuJDqA7jyf4Cm_nPrVHehGA1EdBHXYa5h0Exkmmj79tbW1YFz4MBHyA3FldhIiXc67-P3ivFjgZJRvCRvbd1U5QOU8J5iiN5BlfXgf8b8AWHM0Pr9tIR60L1fgk4OGn0Y5wmqeRfHBDFBmft58GmCl5hi6q_IRdCfO3_9nwvSVo_t9rloXp_qbdkUeq2wcMbRe-GYD1xbZTgGH4xkyIxFu-HBK6kpFSgYt8YaSRk9LkoZQRk6u-YLcnu-PZG6rxwHnQ_dH6070fgv2UVH4A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining</title><source>arXiv.org</source><creator>Zong, Qing ; Wang, Zhaowei ; Xu, Baixuan ; Zheng, Tianshi ; Shi, Haochen ; Wang, Weiqi ; Song, Yangqiu ; Wong, Ginny Y ; See, Simon</creator><creatorcontrib>Zong, Qing ; Wang, Zhaowei ; Xu, Baixuan ; Zheng, Tianshi ; Shi, Haochen ; Wang, Weiqi ; Song, Yangqiu ; Wong, Ginny Y ; See, Simon</creatorcontrib><description>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 text 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.</description><identifier>DOI: 10.48550/arxiv.2310.05210</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2023-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2310.05210$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2310.05210$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zong, Qing</creatorcontrib><creatorcontrib>Wang, Zhaowei</creatorcontrib><creatorcontrib>Xu, Baixuan</creatorcontrib><creatorcontrib>Zheng, Tianshi</creatorcontrib><creatorcontrib>Shi, Haochen</creatorcontrib><creatorcontrib>Wang, Weiqi</creatorcontrib><creatorcontrib>Song, Yangqiu</creatorcontrib><creatorcontrib>Wong, Ginny Y</creatorcontrib><creatorcontrib>See, Simon</creatorcontrib><title>TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining</title><description>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 text 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.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8tKw0AYBeDZuJDqA7jyf4Cm_nPrVHehGA1EdBHXYa5h0Exkmmj79tbW1YFz4MBHyA3FldhIiXc67-P3ivFjgZJRvCRvbd1U5QOU8J5iiN5BlfXgf8b8AWHM0Pr9tIR60L1fgk4OGn0Y5wmqeRfHBDFBmft58GmCl5hi6q_IRdCfO3_9nwvSVo_t9rloXp_qbdkUeq2wcMbRe-GYD1xbZTgGH4xkyIxFu-HBK6kpFSgYt8YaSRk9LkoZQRk6u-YLcnu-PZG6rxwHnQ_dH6070fgv2UVH4A</recordid><startdate>20231008</startdate><enddate>20231008</enddate><creator>Zong, Qing</creator><creator>Wang, Zhaowei</creator><creator>Xu, Baixuan</creator><creator>Zheng, Tianshi</creator><creator>Shi, Haochen</creator><creator>Wang, Weiqi</creator><creator>Song, Yangqiu</creator><creator>Wong, Ginny Y</creator><creator>See, Simon</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20231008</creationdate><title>TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining</title><author>Zong, Qing ; Wang, Zhaowei ; Xu, Baixuan ; Zheng, Tianshi ; Shi, Haochen ; Wang, Weiqi ; Song, Yangqiu ; Wong, Ginny Y ; See, Simon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-dbd194d2ef3ac7b30fefb5202bc0c83fe75a1140423cbcb5121bc077b4120dc63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Zong, Qing</creatorcontrib><creatorcontrib>Wang, Zhaowei</creatorcontrib><creatorcontrib>Xu, Baixuan</creatorcontrib><creatorcontrib>Zheng, Tianshi</creatorcontrib><creatorcontrib>Shi, Haochen</creatorcontrib><creatorcontrib>Wang, Weiqi</creatorcontrib><creatorcontrib>Song, Yangqiu</creatorcontrib><creatorcontrib>Wong, Ginny Y</creatorcontrib><creatorcontrib>See, Simon</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zong, Qing</au><au>Wang, Zhaowei</au><au>Xu, Baixuan</au><au>Zheng, Tianshi</au><au>Shi, Haochen</au><au>Wang, Weiqi</au><au>Song, Yangqiu</au><au>Wong, Ginny Y</au><au>See, Simon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining</atitle><date>2023-10-08</date><risdate>2023</risdate><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 text 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><doi>10.48550/arxiv.2310.05210</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2310.05210 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2310_05210 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Computation and Language |
| title | TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T08%3A55%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=TILFA:%20A%20Unified%20Framework%20for%20Text,%20Image,%20and%20Layout%20Fusion%20in%20Argument%20Mining&rft.au=Zong,%20Qing&rft.date=2023-10-08&rft_id=info:doi/10.48550/arxiv.2310.05210&rft_dat=%3Carxiv_GOX%3E2310_05210%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |