Zoé Chevallier

I am a Postdoctoral Researcher at the University of Verona in Italy, under the supervision of Matteo Lissandrini. My research focus on Data Discovery and Management, with a specific focus on Knowledge Graphs. I am currently involved in the DataGEMS project, specifically on the development of a polyglot query engine.

I obtained my PhD entitled “Data Discovery and Extraction in the Web of Data” in September 2025 in the David Laboratory, University of Versailles Paris Saclay and the local authority Grand Paris Sud. My PhD work was supervised by Zoubida Kedad, Béatrice Finance.

Selected Publications

Identifying Relevant Data in RDF Sources

Zoé Chevallier, Zoubida Kedad, Béatrice Finance, and 1 more author

In Research Challenges in Information Science - 18th International Conference, RCIS 2024, Guimarães, Portugal, May 14-17, 2024, Proceedings, Part II, 2024

Abs DOI

The increasing number of RDF data sources published on the web represents an unprecedented amount of information. However, querying these sources to extract the relevant information for a specific need represented by a target schema is a complex task as the alignment between the target and the source schemas might not be provided or incomplete. This paper presents an approach which aims at automatically populating the classes of a target schema. Our approach relies on a semi-supervised learning algorithm that iteratively identifies instance patterns in the data source that represent candidate instances for the target schema. We present some preliminary experiments showing the effectiveness of our approach.
Generating SPARQL Queries for Data Discovery

Zoé Chevallier, Zoubida Kedad, Béatrice Finance, and 1 more author

In Advances in Databases and Information Systems - 28th European Conference, ADBIS 2024, Bayonne, France, August 28-31, 2024, Proceedings, 2024

Abs DOI

The number of datasets available on the Web represents a huge space of meaningful information. Then done manually, identifying the relevant portion of the data for a specific need is time-consuming. This paper presents an approach that identifies and extracts the relevant portion of RDF data sources for some application requirements described by a target schema. The identification process is based on a semi-supervised learning algorithm that iteratively computes for each class of the target schema the similarity between source entities and both the class description and the candidate instance patterns already identified for this class. The extraction process generates SPARQL queries for the identified candidate instance patterns. We present some evaluations showing the effectiveness of our approach.
Data Search and Discovery in RDF Sources

Zoé Chevallier, Zoubida Kedad, Béatrice Finance, and 1 more author

In The Semantic Web: ESWC 2024 Satellite Events - Hersonissos, Crete, Greece, May 26-30, 2024, Proceedings, Part I, 2024

Abs DOI

The RDF data sources published on the Web represent an unprecedented amount of knowledge. However, querying these sources to extract the relevant information for some specific needs represented by a target schema is a complex task, as the alignment between the target and the source schemas might not be provided or may be incomplete. This paper presents a system that aims to automatically populate the classes of a target schema from RDF data sources by identifying candidate instance patterns. This identification process relies on a semi-supervised learning algorithm and the system automatically generates the SPARQL queries that populate the target schema.