Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

FarFetched: entity-centric reasoning and claim validation for the Greek language based on textually represented environments

Papadopoulos Dimitrios, Metropoulou Katerina, Papadakis Nikolaos, Matsatsinis Nikolaos

Simple record


URIhttp://purl.tuc.gr/dl/dias/58E6B8C0-E427-4789-A029-87AA00A0550C-
Identifierhttps://doi.org/10.1145/3549737.3549749-
Identifierhttps://dl.acm.org/doi/10.1145/3549737.3549749-
Languageen-
Extent12 pagesen
TitleFarFetched: entity-centric reasoning and claim validation for the Greek language based on textually represented environmentsen
CreatorPapadopoulos Dimitriosen
CreatorΠαπαδοπουλος Δημητριοςel
CreatorMetropoulou Katerinaen
CreatorPapadakis Nikolaosen
CreatorMatsatsinis Nikolaosen
CreatorΜατσατσινης Νικολαοςel
PublisherAssociation for Computing Machinery (ACM)en
DescriptionThe research work of Dimitris Papadopoulos was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number: 50, 2nd call).en
Content SummaryOur collective attention span is shortened by the flood of online information. With FarFetched, we address the need for automated claim validation based on the aggregated evidence derived from multiple online news sources. We introduce an entity-centric reasoning framework in which latent connections between events, actions, or statements are revealed via entity mentions and represented in a graph database. Using entity linking and semantic similarity, we offer a way for collecting and combining information from diverse sources in order to generate evidence relevant to the user’s claim. Then, we leverage textual entailment recognition to quantitatively determine whether this assertion is credible, based on the created evidence. Our approach tries to fill the gap in automated claim validation for less-resourced languages and is showcased on the Greek language, complemented by the training of relevant semantic textual similarity (STS) and natural language inference (NLI) models that are evaluated on translated versions of common benchmarks.en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by-nc-nd/4.0/en
Date of Item2024-09-17-
Date of Publication2022-
SubjectClaim validationen
SubjectEntity linkingen
SubjectNatural language inferenceen
SubjectSemantic textual similarityen
SubjectLow-resource languagesen
Bibliographic CitationD. Papadopoulos, K. Metropoulou, N. Papadakis, and N. Matsatsinis, “FarFetched: entity-centric reasoning and claim validation for the Greek language based on textually represented environments,” in Proceedings of the 12th Hellenic Conference on Artificial Intelligence (SETN 2022), Sep. 2022, doi: 10.1145/3549737.3549749.en

Available Files

Services

Statistics