Search Results for author: Virginie Mouilleron

Found 8 papers, 0 papers with code

The Financial Document Structure Extraction Shared task (FinToc 2020)

no code implementations FNP (COLING) 2020 Najah-Imane Bentabet, Rémi Juge, Ismail El Maarouf, Virginie Mouilleron, Dialekti Valsamou-Stanislawski, Mahmoud El-Haj

This paper presents the FinTOC-2020 Shared Task on structure extraction from financial documents, its participants results and their findings.

Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detection

no code implementations16 Dec 2024 Arij Riabi, Virginie Mouilleron, Menel Mahamdi, Wissam Antoun, Djamé Seddah

The proliferation of radical content on online platforms poses significant risks, including inciting violence and spreading extremist ideologies.

Fairness

Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks

no code implementations25 Jun 2024 Arij Riabi, Menel Mahamdi, Virginie Mouilleron, Djamé Seddah

Protecting privacy is essential when sharing data, particularly in the case of an online radicalization dataset that may contain personal information.

Classification

Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?

no code implementations9 Jun 2023 Wissam Antoun, Virginie Mouilleron, Benoît Sagot, Djamé Seddah

This paper proposes a methodology for developing and evaluating ChatGPT detectors for French text, with a focus on investigating their robustness on out-of-domain data and against common attack schemes.

Adversarial Text Language Modeling +1

Radarly : \'ecouter et analyser le web conversationnel en temps r\'eel (Real time listening and analysis of the social web using Radarly)

no code implementations JEPTALNRECITAL 2016 Jade Copet, Christine de Carvalho, Virginie Mouilleron, Benoit Tabutiaux, Hugo Zanghi

De par le contexte conversationnel digital, l{'}outil Radarly a {\'e}t{\'e} con{\c{c}}u pour permettre de traiter de grands volumes de donn{\'e}es h{\'e}t{\'e}rog{\`e}nes en temps r{\'e}el, de g{\'e}n{\'e}rer de nouveaux indicateurs et de les visualiser sur une interface coh{\'e}rente et confortable afin d{'}en tirer des analyses et {\'e}tudes pertinentes.

Cannot find the paper you are looking for? You can Submit a new open access paper.