I'm a

Arij Riabi

Learn More

Who am I? About Me

Hi! I'm Arij

I am a final year Ph.D. student in the ALMAnaCH lab at Inria Paris, under the supervision of Djamé Seddah and Laurent Romary. My research interests include low-resource languages, user-generated content, hate speech and radical content detection, dataset creation, and addressing bias in NLP.

My Experience Resume

Education

  • Doctoral Researcher (Ph.D. student)

    Inria (ALMAnaCH lab) and Sorbonne University (Paris, France)
    October 2021 – present

  • Master’s in Data Science and Artificial Intelligence

    Sorbonne University (formerly: Pierre et Marie Curie University)
    2018 - 2020

  • Bachelor’s in Computer Science (3rd year as Erasmus student)

    Pierre-et-Marie-Curie University, Paris.
    2017 - 2018

  • Bachelor’s in Computer Science (1st & 2nd years)

    Higher Institute of Computer Science and Mathematics of Monastir, Tunisia.
    2015 - 2017

Teaching

  • Engineering Diploma (2nd year): Applied Statistics (or Econometrics) Project

    ENSAE Paris
    January 2022 - Mai 2023

  • Bachelor (1st year): Programming in Python

    Bachelor in Computer Science
    University Paris-Est Créteil Val de Marne, France.
    September 2021 - May 2022

Experience

  • Research Engineer

    Inria – ALMAnaCH Team, Paris
    October 2020 – September 2021

    NLP for non-standard and under-resourced language varieties focused on North African Arabic dialects written in the Latin alphabet.

  • Master 2 internship

    ReciTAL, Paris
    February 2020 – August 2020

    Research on data augmentation and transfer learning to improve question-answering systems.

  • Research Assistant Internship

    MLIA team at LIP6, Sorbonne University (formerly Pierre et Marie Curie University)
    June 2019 – August 2019

    Named Entity Recognition (NER) within the context of medical documents.

  • Developer Internship

    Wealzy, Paris
    June 2018 – September 2019

    Identification of properties of interest for investment online.

My Scientific Papers Publications

Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detection
2025
Arij Riabi, Virginie Mouilleron, Menel Mahamdi, Wissam Antoun and Djamé Seddah.
International Conference on Computational Linguistics (COLING2025)
Link to the paper

Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties
2025
Javier A. Lopetegui, Arij Riabi, Djamé Seddah
Workshop on NLP for Similar Languages, Varieties and Dialects (VARDIAL2025)
Link to the paper

Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks
2024
Arij Riabi, Menel Mahamdi, Virginie Mouilleron, Djamé Seddah
Workshop on Privacy in Natural Language Processing (PrivateNLP2024)
Link to the paper

Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark
2024
Stephen Mayhew, Terra Blevins, Shuheng Liu, Marek Suppa, Hila Gonen, Joseph Marvin Imperial, Börje F. Karlsson, Peiqin Lin, Nikola Ljubešić, Lester James Validad Miranda, Barbara Plank, Arij Riabi, Yuval Pinter
North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Link to the paper

Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language
2023
Arij Riabi, Menel Mahamdi, Djamé Seddah
Linguistic Annotation Workshop (LAW-XVII)
Link to the paper

Analyzing Zero-Shot transfer Scenarios across Spanish variants for Hate Speech Detection
2023
Galo Castillo-lópez, Arij Riabi, Djamé Seddah
Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
Link to the paper

Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
2022
Arij Riabi,Syrielle Montariol, Djamé Seddah
Findings of the Association for Computational Linguistics: AACL-IJCNLP
Link to the paper

Tâches Auxiliaires Multilingues pour le Transfert de Modèles de Détection de Discours Haineux
2022
Arij Riabi, Syrielle Montariol, Djamé Seddah
Conférence sur le Traitement Automatique des Langues Naturelles
Link to the paper

Fine-tuning and Sampling Strategies for Multimodal Role Labeling of Entities under Class Imbalance
2022
Syrielle Montariol, Étienne Simon, Arij Riabi, Djamé Seddah
Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations
Link to the paper

Can Character-based Language Models Improve Downstream Task Performances In Low-Resource And Noisy Language Scenarios?
2021
Arij Riabi, Benoît Sagot, Djamé Seddah
Workshop on Noisy User-generated Text (W-NUT)
Link to the paper

Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering

2021
Arij Riabi, Thomas Scialom, Rachel Keraron, Benoît Sagot, Djamé Seddah, Jacopo Staiano
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Link to the paper

Get in Touch Contact Me

Email

arij.riabi@inria.fr

Visit

Inria Paris, 48 Rue Barrault, 75013 Paris