• Tailoring Scientific Argument...

Treffer: Tailoring Scientific Argument Mining for Scientific Literature Correction

Title:
Tailoring Scientific Argument Mining for Scientific Literature Correction
Authors:
Ozturk, Yagmur, Labbé, Cyril, Portet, François
Contributors:
Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP), Laboratoire d'Informatique de Grenoble (LIG), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP), Université Grenoble Alpes (UGA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP), Université Grenoble Alpes (UGA), Systèmes d’Information - inGénierie et Modélisation Adaptables (SIGMA), European Project: 951393,ERC-2020-SyG,ERC-2020-SyG,NanoBubbles(2021)
Source:
Journée Natural Language Argumentation – GDR TAL – GDR RADIA, Nov 2023, Valbonne, France
Publisher Information:
CCSD, 2023.
Publication Year:
2023
Collection:
collection:UGA
collection:CNRS
collection:INPG
collection:LIG
collection:LIG_GLSI_SIGMA
collection:LIG_TDCGE_GETALP
collection:UGA-EPE
collection:LIG_SIDCH
collection:TEST-UGA
Subject Terms:
ARGUMENT MINING, SCIENTIFIC DOCUMENT PROCESSING, NATURAL LANGUAGE PROCESSING, SCIENTIFIC LITERATURE CORRECTION, SCIENTIFIC ARGUMENT MINING, [INFO]Computer Science [cs]
Subject Geographic:
Valbonne, France
Original Identifier:
HAL: hal-04346693
Document Type:
Konferenz conferenceObject<br />Conference poster
Language:
English
Relation:
info:eu-repo/grantAgreement//951393/EU/Nano bubbles: how, when and why does science fail to correct itself?/NanoBubbles
Access URL:
https://hal.science/hal-04346693
https://hal.science/hal-04346693v1/document
https://hal.science/hal-04346693v1/file/Ozturk_Poster.pdf
Rights:
info:eu-repo/semantics/OpenAccess
Accession Number:
edshal.hal.04346693v1
Database:
HAL

Weitere Informationen

In this study, we examine the potential application of Scientific Argument Mining (SAM) in enhancing scientific literature correction processes. Specifically, we focus on evaluating SAM's effectiveness in assessing the influence of retracted citations on the accuracy of claims and results within the field of nanobiology. Our objectives include creating a novel SAM dataset derived from nanobiology articles, assessing the adaptability of current SAM frameworks to this new dataset, and offering a comprehensive synthesis of the existing SAM guidelines for scientific literature correction practices.