About Me
I am a NLP researcher at CEA LIST working with the industry at the frontier of research 🚀.
I am also fighting disinformation and polarization by devising new methods for news recommendation and bot detection.
And I like running, a lot.
🗞️ News #
- [2023-12-20] Aboubacar Tuo has successfully defended its thesis 🎉
- [2023-12-11] Guilhem Piat has successfully defended its thesis 🎉
- [2023-10-24] Our paper "TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation" has been accepted to WACV 2024. 🎉
- [2023-10-24] Our consortium OpenLLM-France, lead by Linagora, has submitted its proposal to the call entitled "Communs numériques pour l’intelligence artificielle générative"
📋 Current Projects & Collaborations #
VANGUARD - Disrupting trafficking in human beings
Information extraction from web and social media resources
HE / EU contribution: € 5,000,000 / Duration: 36m (2023-10 - 2026-09)
eMeuse Santé
Information extraction for clinical trials
🎓 Supervision #
Current
- Hugo Boulanger (postdoc, 2023-2024): Text Generation
- Paul Grimal (PhD student, 2022-2025): Multi-modality, Diffusion Models
- Evan Dufraisse (PhD student, 2021-2024): Aspect-Based Sentiment Analysis
Past
- Aboubacar Tuo (PhD student, 2020-2023): Event Extraction, Few-shot learning
- Guilhem Piat (PhD student, 2019-2023): Named Entity Recognition, Entity Linking, BioNLP
- Rida Lali (intern, 2023): Event Extraction, Knowledge Injection
- Babacar Sow (intern, 2021): DeepFake Detection
- Salma Salhi (intern, 2020): Event Extraction
📚 Publications #
2024
TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2024.
Direct Link
2023
MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification
In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023.
Direct Link
Détection d'événements à partir de peu d'exemples par seuillage dynamique
In: Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles. 2023.
Direct Link
Intégration de connaissances structurées par synthèse de texte spécialisé
In: Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles. 2023.
Ask Me
Trigger or Not Trigger: Dynamic Thresholding for Few Shot Event Detection
In: Proceedings of the 45th European Conference on Information Retrieval. 2023.
Direct Link Ask Me
Analysis of Polarization in the News
In: Workshop on fake news "Infox sur Seine". 2023.
Ask Me
2022
Enriching Contextualized Representations with Biomedical Ontologies: Extending KnowBert to UMLS
In: Proceedings of the 2022 Computing Conference. 2022.
Direct Link Ask Me
Mieux utiliser BERT pour la détection d'évènements à partir de peu d'exemples
In: Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. 2022.
Direct Link
Stratégies d'adaptation pour la reconnaissance d'entités médicales en français
In: Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. 2022.
Direct Link
Don't Burst Blindly: For a Better Use of Natural Language Processing to Fight Opinion Bubbles in News Recommendations
In: Proceedings of the LREC 2022 workshop on Natural Language Processing for Political Sciences. 2022.
Direct Link
Automatic Detection of Bot-generated Tweets
In: Proceedings of the 1st Workshop on Multimedia AI against Disinformation. 2022.
Direct Link Ask Me
Better Exploiting BERT for Few-shot Event Detection
In: Proceedings of the 27th International Conference on Natural Language and Information Systems. 2022.
Direct Link Ask Me
2020
Modèle neuronal pour la résolution de la coréférence dans les dossiers médicaux électroniques
In: Actes de la 27e conférence sur Traitement Automatique des Langues Naturelles. 2020.
Direct Link Slides
2018
Extracting Clinical Event Timelines: Temporal Information Extraction and Coreference Resolution in Electronic Health Records
Université Paris-Saclay, 2018.
Direct Link
Evaluation of a Sequence Tagging Tool for Biomedical Texts
In: Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis. 2018.
Direct Link Slides
2017
LIMSI-COT at SemEval-2017 Task 12: Neural Architecture for Temporal Information Extraction from Clinical Narratives
In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017). 2017.
Direct Link Slides
Neural Architecture for Temporal Relation Extraction: A Bi-LSTM Approach for Detecting Narrative Containers
In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 2017.
Direct Link Poster
Temporal information extraction from clinical text
In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. 2017.
Direct Link Poster
2016
Extraction de relations temporelles dans des dossiers électroniques patient
In: Actes de la 23e Conférence sur le Traitement Automatique des Langues Naturelles. 2016.
Direct Link Poster
LIMSI-COT at SemEval-2016 Task 12: Temporal relation identification using a pipeline of classifiers
In: Proceedings of the 10th International Workshop on Semantic Evaluation. 2016.
Direct Link Poster Slides
👨💻 Open Source #
I am just starting giving back to the community by providing some (I hope) useful tools and libraries.
This is an ongoing effort, the list will hopefully get larger over time !