HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Master Thesis

Détection d’affirmation et de contre-affirmation dans la littérature scientifique

Abstract : Scientific claim verification is a new task that has recently emerged in NLP. It aims to verify the truthfulness of a scientific claim and find evidence in a scientific corpus. The evidence could be a text, or a sentence extracted from the corpus, which supports or contradicts the claim. In this paper, we use two architectures to design our system for claim verification and label prediction. The task is divided into three steps: first we retrieve the evidence abstracts from the corpus, then we select the evidence sentences from the retrieved abstracts and finally we label the evidence sentences as supporting or contradicting the claim.
Document type :
Master Thesis
Complete list of metadata

Contributor : Uga - Llasic Sciences Du Langage & Fles Connect in order to contact the contributor
Submitted on : Friday, January 7, 2022 - 11:55:43 AM
Last modification on : Friday, January 21, 2022 - 4:14:02 AM
Long-term archiving on: : Friday, April 8, 2022 - 6:45:33 PM


DENG Wenjing_M2_IDL.pdf
Files produced by the author(s)


  • HAL Id : dumas-03516607, version 1


Wenjing Deng. Détection d’affirmation et de contre-affirmation dans la littérature scientifique. Sciences de l'Homme et Société. 2021. ⟨dumas-03516607⟩



Record views


Files downloads