PhD: RDF-to-Text Extraction for Collaborative Wiki Editing

1000scholars; Valbonne; Sur place; EUR 22 000 - 29 000; Plein temps

Résumé du poste

INRIA is seeking a PhD candidate to work on extracting structured RDF knowledge from unstructured text and to verbalize it for collaborative editing of wikis and linked data. The project focuses on neuro-symbolic collaboration, provenance, and traceability between natural language and graphs.

You will explore SHACL shapes, graph-pattern-based validation, and grounded language generation to ensure semantic fidelity and explainability. Proficiency in NLP, semantic Web, and ML is expected.

Qualifications

• Expertise in knowledge graphs, linked data, semantic Web, ML, NLP, and neuro-symbolic approaches.
• Fluent English and French language skills are valued.
• Strong teamwork and open-source community experience (desirable).

Responsabilités

• Develop language-model-based methods to extract RDF knowledge from texts while preserving ontology fidelity.
• Design SHACL shapes and domain/range constraints to guide knowledge extraction.
• Create verbalization techniques to convert RDF subgraphs into fluent natural language.
• Evaluate extraction accuracy, recall, and semantic alignment with the knowledge graph.

Connaissances

Knowledge graphs

Semantic Web

NLP & ML

Neuro-symbolic approaches

Team collaboration

Description du poste

INRIA is seeking a PhD candidate to work on extracting structured RDF knowledge from unstructured text and to verbalize it for collaborative editing of wikis and linked data. The project focuses on neuro-symbolic collaboration, provenance, and traceability between natural language and graphs.

You will explore SHACL shapes, graph-pattern-based validation, and grounded language generation to ensure semantic fidelity and explainability. Proficiency in NLP, semantic Web, and ML is expected.