Automated Fact Checking in the News Room

Miranda, Sebastião; Nogueira, David Silva; Mendes, Afonso; Vlachos, Andreas; Secker, Andrew; Garrett, Rebecca; Mitchel, Jeff; Marinho, Zita

doi:10.1145/3308558.3314135

Cited by 24 publications

(21 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In either case, it is important to model the reliability of the source as well as the stance of the claim with respect to other claims; in fact, it has been proposed that a claim can be fact-checked based on its source alone (Baly et al, 2018a) or based on its stance alone (Dungs et al, 2018). A third direction performs fact-checking against Wikipedia (Thorne et al, 2018;Nie et al, 2019), or against a general collection of documents (Miranda et al, 2019). A fourth direction uses a knowledge base or a knowledge graph (Ciampaglia et al, 2015;Shiadralkar et al, 2017;Gad-Elrab et al, 2019a,b;Huynh and Papotti, 2019).…”

Section: Related Workmentioning

confidence: 99%

That is a Known Lie: Detecting Previously Fact-Checked Claims

Shaar¹,

Babulkov²,

Martino³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

The recent proliferation of "fake news" has triggered a number of responses, most notably the emergence of several manual fact-checking initiatives. As a result and over time, a large number of fact-checked claims have been accumulated, which increases the likelihood that a new claim in social media or a new statement by a politician might have already been factchecked by some trusted fact-checking organization, as viral claims often come back after a while in social media, and politicians like to repeat their favorite statements, true or false, over and over again. As manual fact-checking is very time-consuming (and fully automatic fact-checking has credibility issues), it is important to try to save this effort and to avoid wasting time on claims that have already been fact-checked. Interestingly, despite the importance of the task, it has been largely ignored by the research community so far. Here, we aim to bridge this gap. In particular, we formulate the task and we discuss how it relates to, but also differs from, previous work. We further create a specialized dataset, which we release to the research community. Finally, we present learning-to-rank experiments that demonstrate sizable improvements over state-of-the-art retrieval and textual similarity approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

That is a Known Lie: Detecting Previously Fact-Checked Claims

Shaar¹,

Babulkov²,

Martino³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Na literatura, vários trabalhos lidam diretamente com o problema da verificac ¸ão de fatos [Santos and Pardo 2020, Miranda et al 2019, Gerber et al 2015. No entanto, de acordo com [Graves 2018], é importante automatizar não apenas a verificac ¸ão, mas também etapas de identificac ¸ão e gerac ¸ão de resultados.…”

Section: Trabalhos Relacionadosunclassified

ReVera Framework: Um Framwork para rastreabilidade em fact-checking automático

Souza

Assis

Mendonça

et al. 2021

Anais Do XIII Simpósio Brasileiro De Tecnologia Da Informação E Da Linguagem Humana (STIL 2021)

View full text Add to dashboard Cite

A verificação manual de fatos tende a ser cara e a escalabilidade desafiadora, incentivando a busca por métodos automáticos. Porém, esses métodos foram criados com arquiteturas monolíticas, não fazendo uso de peças pré-construídas e são mais difíceis de serem compreendidos por terceiros. Este trabalho tem como objetivo propor um framework, onde o desenvolvimento de métodos pode ser feito de forma modular, criando ﬂuxos de trabalho baseados em etapas-chave que podem ser interligadas para gerar a classificação de entrada. O framework faz uso de uma ontologia de rastreabilidade proposta para mapear todos os dados gerados durante a execução sob um vocabulário unificado, o que facilita a comunicação entre esses componentes independentes.

show abstract

“…The second model consists of a customised search engine, Priberam Search, based on inverted indexing and retrieval using the Okapi-BM25 algorithm [4].…”

Section: Priberam Searchmentioning

confidence: 99%

“…To use the Priberam Search Engine, we first indexed the training set taking into account the abstract text, title, complete set of gold DeCS codes, and also their corresponding string descriptors along with some synonyms provided 4 . We tuned the number of neighbours k = [10,20,30,40,50,60,70,100,200] in the development set for the k-NN algorithm and obtained the best results for k = 40.…”

Section: Priberam Searchmentioning

confidence: 99%

“…This paper describes our participation at the BioASQ task Mesinesp. We explore the performance of a one-vs.-rest model based on Support Vector Machines (SVM) [3] as well as that of a proprietary search engine, Priberam Search [4], which relies on inverted indexes combined with a k-nearest neighbours classifier. Furthermore, we took advantage of BERT's contextualised embeddings [5] and tested three possible classifiers: a linear classifier; a label attention mechanism that leverages label semantics; and a recurrent model that predicts a sequence of labels according to their frequency.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Priberam at MESINESP Multi-label Classification of Medical Texts Task

Cardoso¹,

Marinho²,

Mendes³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Medical articles provide current state of the art treatments and diagnostics to many medical practitioners and professionals. Existing public databases such as MEDLINE contain over 27 million articles, making it difficult to extract relevant content without the use of efficient search engines. Information retrieval tools are crucial in order to navigate and provide meaningful recommendations for articles and treatments. Classifying these articles into broader medical topics can improve the retrieval of related articles [1]. The set of medical labels considered for the MESINESP task is on the order of several thousands of labels (DeCS codes), which falls under the extreme multi-label classification problem [2]. The heterogeneous and highly hierarchical structure of medical topics makes the task of manually classifying articles extremely laborious and costly. It is, therefore, crucial to automate the process of classification. Typical machine learning algorithms become computationally demanding with such a large number of labels and achieving better recall on such datasets becomes an unsolved problem. This work presents Priberam's participation at the BioASQ task Mesinesp. We address the large multi-label classification problem through the use of four different models: a Support Vector Machine (SVM) [3], a customised search engine (Priberam Search) [4], a BERT based classifier [5], and a SVM-rank ensemble [6] of all the previous models. Results demonstrate that all three individual models perform well and the best performance is achieved by their ensemble, granting Priberam the 6-th place in the present challenge and making it the 2-nd best team.

show abstract

Automated Fact Checking in the News Room

Cited by 24 publications

References 9 publications

That is a Known Lie: Detecting Previously Fact-Checked Claims

That is a Known Lie: Detecting Previously Fact-Checked Claims

ReVera Framework: Um Framwork para rastreabilidade em fact-checking automático

Priberam at MESINESP Multi-label Classification of Medical Texts Task

Contact Info

Product

Resources

About