東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Multilingual, Multimodal and Explain...

Cekinel, Recep Firat,

Linked to FindBook

Google Book

Amazon

博客來

Multilingual, Multimodal and Explainable Approaches for Automated Fact-Checking Problem = = Otomatik Dogruluk Kontrolu Problemi Icin Cok Dilli, Cok Modlu ve Aciklanabilir Yaklasimlar /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Multilingual, Multimodal and Explainable Approaches for Automated Fact-Checking Problem =/ Recep Firat Cekinel.
Reminder of title:	Otomatik Dogruluk Kontrolu Problemi Icin Cok Dilli, Cok Modlu ve Aciklanabilir Yaklasimlar /
Author:	Cekinel, Recep Firat,
Description:	1 electronic resource (137 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-10, Section: A.
Contained By:	Dissertations Abstracts International86-10A.
Subject:	Public opinion. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31929043
ISBN:	9798311935135

Multilingual, Multimodal and Explainable Approaches for Automated Fact-Checking Problem = = Otomatik Dogruluk Kontrolu Problemi Icin Cok Dilli, Cok Modlu ve Aciklanabilir Yaklasimlar /
Cekinel, Recep Firat,

Multilingual, Multimodal and Explainable Approaches for Automated Fact-Checking Problem =Otomatik Dogruluk Kontrolu Problemi Icin Cok Dilli, Cok Modlu ve Aciklanabilir Yaklasimlar /Recep Firat Cekinel. - 1 electronic resource (137 pages)

Source: Dissertations Abstracts International, Volume: 86-10, Section: A.

Automated fact-checking methods primarily rely on content-based approaches, utilizing deep neural networks to extract sophisticated features from text for prediction. However, the inherently black-box nature of these models makes their decision-making processes challenging to interpret. Another challenge for automated fact-checking models is their dependence on language-specific data, with limited multilingual datasets available for training. Moreover, the multimodal nature of fake posts-including text, images, and speech-presents an additional challenge. This thesis addresses automated fact-checking research, aiming to predict the veracity of claims while extending contributions to explainable solutions for fact-checking and sarcasm detection. We propose explainable models through multi-task learning and causal inference, evaluate cross-lingual transfer learning for low-resource languages, and examine how recent VLMs utilize text and image information for fact-checking. Our multi-task learning approach involves a T5-based encoder-decoder model trained for text summarization and veracity prediction, with generated summaries serving as explanations for predicted veracity labels. Moreover, a Turkish fact-checking dataset is released and experiments are conducted using transfer learning and machine translation to address data scarcity. In multimodality, we investigate VLMs' effectiveness in representing text and image information, finding that while multimodal embeddings generally enhance performance, discrete text-only and image-only models often outperform them. Lastly, we apply causal inference to text analysis, examining how sarcastic linguistic features and punctuation impact text popularity and leveraging clustering and topic modeling to uncover latent information on irony and popularity.

English

ISBN: 9798311935135Subjects--Topical Terms:

531264
Public opinion.

Multilingual, Multimodal and Explainable Approaches for Automated Fact-Checking Problem = = Otomatik Dogruluk Kontrolu Problemi Icin Cok Dilli, Cok Modlu ve Aciklanabilir Yaklasimlar /
LDR:05222nmm a22003733i 4500 001 2433254
005 20250825104033.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798311935135
035 $a (MiAaPQD)AAI31929043
035 $a (MiAaPQD)MiddleEastTech113463
035 $a AAI31929043
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Cekinel, Recep Firat, $e author. $3 3822791
245 1 0 $a Multilingual, Multimodal and Explainable Approaches for Automated Fact-Checking Problem = $b Otomatik Dogruluk Kontrolu Problemi Icin Cok Dilli, Cok Modlu ve Aciklanabilir Yaklasimlar / $c Recep Firat Cekinel.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (137 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-10, Section: A.
500 $a Advisors: Karagoz, Pinar.
502 $b Ph.D. $c Middle East Technical University (Turkey) $d 2025.
520 $a Automated fact-checking methods primarily rely on content-based approaches, utilizing deep neural networks to extract sophisticated features from text for prediction. However, the inherently black-box nature of these models makes their decision-making processes challenging to interpret. Another challenge for automated fact-checking models is their dependence on language-specific data, with limited multilingual datasets available for training. Moreover, the multimodal nature of fake posts-including text, images, and speech-presents an additional challenge. This thesis addresses automated fact-checking research, aiming to predict the veracity of claims while extending contributions to explainable solutions for fact-checking and sarcasm detection. We propose explainable models through multi-task learning and causal inference, evaluate cross-lingual transfer learning for low-resource languages, and examine how recent VLMs utilize text and image information for fact-checking. Our multi-task learning approach involves a T5-based encoder-decoder model trained for text summarization and veracity prediction, with generated summaries serving as explanations for predicted veracity labels. Moreover, a Turkish fact-checking dataset is released and experiments are conducted using transfer learning and machine translation to address data scarcity. In multimodality, we investigate VLMs' effectiveness in representing text and image information, finding that while multimodal embeddings generally enhance performance, discrete text-only and image-only models often outperform them. Lastly, we apply causal inference to text analysis, examining how sarcastic linguistic features and punctuation impact text popularity and leveraging clustering and topic modeling to uncover latent information on irony and popularity.
520 $a Otomatik dogruluk kontrolu yontemleri, agirlikli olarak icerik tabanli yaklasimlara dayanmakta ve tahmin icin metinden sofistike ozellikler cikarmak uzere derin sinir aglarini kullanmaktadir. Ancak, bu modellerin dogasi geregi kara kutu olusu, karar verme sureclerinin anlasilmasini zorlastirmaktadir. Otomatik dogruluk kontrolu modelleri icin bir diger zorluk, dil spesifik verilere olan bagimliliklaridir ve egitim icin mevcut cok dilli veri kumeleri sinirlidir. Ayrica, sahte gonderilerin metin, gorseller ve konusma gibi cok modlu yapisi ek bir zorluk teskil etmektedir. Bu tez, otomatik dogruluk kontrolu arastirmalarini ele alarak iddialarin dogruluklarini tahmin etmeyi hedeflemekte ve dogruluk kontrolu ile alaycilik tespiti icin aciklanabilir cozumler gelistirmeye katki saglamaktadir. Cok gorevli ogrenme ve nedensel cikarim yoluyla aciklanabilir modeller onermekte, dusuk kaynakli diller icin capraz dilli aktarim yoluyla ogrenimini degerlendirmekte ve son donemdeki Gorsel-Dil Modellerining (GDM) dogruluk kontrolu icin metin ve gorsel bilgiyi nasil kullandigini incelemekteyiz. Cok gorevli ogrenme yaklasimimiz, metin ozetleme ve dogruluk tahmini icin egitilmis T5 tabanli bir kodlayici-cozucu modelini icermektedir; olusturulan ozetler, tahmin edilen dogruluk etiketleri icin aciklamalar olarak kullanilmaktadir. Ayrica, Turkce bir dogruluk kontrolu veri kumesi yayimlanmis ve veri yetersizligini ele almak icin transfer ogrenimi ve makine cevirisi kullanilarak deneyler gerceklestirilmistir. Cok modluluk baglaminda, GDM'nin metin ve gorsel bilgiyi temsil etme etkinligini arastirmakta ve cok modlu gomme yontemlerinin genelde performansi artirmasina ragmen, yalnizca metin veya yalnizca gorsel tabanli modellerin siklikla daha iyi sonuc verdigini bulmaktayiz. Son olarak, metin analizinde nedensel cikarimi uygulayarak alayci dilsel ozelliklerin ve noktalamanin metin populerligi uzerindeki etkisini incelemekte ve ironi ve populerlik hakkinda ortuk bilgileri ortaya cikarmak icin kumeleme ve konu modellemeyi kullanmaktayiz.
546 $a English
590 $a School code: 2013
650 4 $a Public opinion. $3 531264
650 4 $a Language. $3 643551
650 4 $a Text categorization. $3 3689475
650 4 $a Neural networks. $3 677449
650 4 $a Decision making. $3 517204
650 4 $a False information. $3 3564362
650 4 $a Machine translation. $3 3687988
650 4 $a Multilingualism. $3 598147
650 4 $a Clustering. $3 3559215
650 4 $a Large language models. $3 3775019
650 4 $a Image. $2 rasuqam $3 1548898
690 $a 0679
710 2 $a Middle East Technical University (Turkey). $b Department of Computer Engineering. $e degree granting institution. $3 3821962
720 1 $a Karagoz, Pinar $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-10A.
790 $a 2013
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31929043