Pierre-Henri Paris
Postdoctoral Researcher in Artificial Intelligence
Institut Polytechnique de Paris
Telecom Paris
Biography
I will begin a position as a Maître de Conférences (Associate Professor) at Paris-Saclay University in September 2024. Currently, I am a postdoctoral researcher at Télécom Paris, Institut Polytechnique de Paris. During my PhD at Conservatoire National des Arts et Métiers and Sorbonne University, I focused on entity linking and data quality of knowledge graphs.
My research interests include artificial intelligence, knowledge graphs, and natural language processing.
Interests
- Artificial Intelligence
- Knowlegde Graphs
- Information Extraction
- Knowledge Representation
- NLP
Education
PhD in Artificial Intelligence, 2020
Sorbonne University and CNAM
M.Sc. in Artificial Intelligence, 2016
CNAM
M.Sc. in Mathematics, 2008
CY Cergy Paris University (incomplete)
Research Interests
Experience
Associate Professor (Maître de Conférences)
Postdoctoral Researcher
Telecom Paris
Works on LLM, logic, and knowledge graphs.
Responsibilities include:
- Collaborations with industrial and academic partners
- Managing meetings with partners
- PhD and student supervision
Researcher
Sorbonne University and CNAM
Entity linking and data quality of knowledge graphs.
Researcher
IGN
Approach aimed at exploring historical texts describing a diachronic phenomenon based on named-entity linking.
Software Engineer
LGC
Responsibilities include:
- Requirements analysis, solution design, development, testing and validation, maintenance, documentation to meet the company’s needs for various projects: e-commerce sites, inventory management, embedded systems, etc.
- Student supervision
- Team management
Supervision involvement
- Simon Coumes: PhD student at Telecom Paris (2022-)
- Chadi Helwe: PhD student at Telecom Paris (2022-2024)
- François Amat: PhD student at Telecom Paris (2022-)
- Syrine El Aoud: master student research project at Telecom Paris (2021)
- Khalil Halloul: BSc student (2013-2014)
- Ayoub Mountassir: MSc student (2013-2015)
- Master student groups at Telecom Paris for student projects
Projects
The last version of the Yago knowledge base is out!
This enhanced version of the YAGO knowledge base integrates extensive elements of the Wikidata taxonomy, providing a cleaner, logically consistent structure for improved information retrieval and automated reasoning.
This enhanced version of the YAGO knowledge base integrates extensive elements of the Wikidata taxonomy, providing a cleaner, logically consistent structure for improved information retrieval and automated reasoning.
MAFALDA is a new benchmark for fallacy classification that consolidates previous datasets into a unified taxonomy. The benchmark includes manual annotations with explanations, a specialized annotation scheme for subjective NLP tasks, and a novel evaluation method to handle subjectivity. We assessed both language models and human performance on MAFALDA to evaluate their fallacy detection and classification capabilities.
The NoRDF Project is a scientific project at Telecom Paris that aims to model and extract complex information from natural language text. More precisely, we want to enrich knowledge bases with events, causation, conditions, precedence, stories, negation, and beliefs.
Recent Publications
Quickly discover relevant content by filtering publications.
(2024).
YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy.
SIGIR 2024.
(2024).
MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification.
NAACL 2024.
(2021).
Non-named Entities - The Silent Majority.
The Semantic Web: ESWC 2021 Satellite Events - Virtual Event, June 6-10, 2021, Revised Selected Papers.
(2021).
The Vagueness of Vagueness in Noun Phrases.
3rd Conference on Automated Knowledge Base Construction, AKBC 2021, Virtual, October 4-8, 2021.
(2020).
A Study About the Use of OWL 2 Semantics in RDF-Based Knowledge Graphs.
The Semantic Web: ESWC 2020 Satellite Events - ESWC 2020 Satellite Events, Heraklion, Crete, Greece, May 31 - June 4, 2020, Revised Selected Papers.