PhD Position F/M [PhD Thesis] Extracting from and verbalizing RDF to text to support collaborative co-editing of wikis and their corresponding linked data

1000scholars; Valbonne; On-site; EUR 22,000 - 29,000; Full time

Job summary

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).

Responsibilities

• 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.

Skills

Knowledge graphs

Semantic Web

NLP & ML

Neuro-symbolic approaches

Team collaboration

Job description

Context

INRIA is the French national research institute dedicated to computer science and applied mathematics and is a founding member of the World-Wide Web Consortium (W3C). The Inria centre at Université Côte d'Azur includes 42 research teams and 9 support services. The centre's staff (about 500 people) is made up of scientists of different nationalities, engineers, technicians, and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM ...), but also with the regional economic players.

Assignment

Large-scale collaborative platforms such as Wikipedia have demonstrated that distributed communities can maintain shared knowledge at scale. Yet the emergence of Large Language Models (LLMs) redefines the conditions of collaboration: trained on human knowledge, these models can now produce and revise it, raising new questions about coherence, authorship, and trust. The project KGTWIN addresses these questions through a new paradigm of neuro-symbolic collaborative editing, in which free text and structured Knowledge Graphs (KGs) co-evolve as complementary representations of the same knowledge. The shared KG acts as the semantic backbone of human–AI collaboration. It maintains consistency across documents, exposes contradictions between texts that refer to the same concepts, and links contributors working on related entities. In this context, the KG provides a verifiable, traceable foundation for shared knowledge, transforming human–AI interaction from sequential exchange into continuous co-evolution.

KGTWIN models this co-evolution as an iterative cycle combining controlled extraction, semantic synchronization, and grounded generation. Controlled extraction uses LLMs to instantiate ontologies and thesauri from collaboratively written texts while preserving provenance. Semantic synchronization detects inconsistencies and propagates updates between textual and graph representations. Grounded generation produces text fragments from coherent subgraphs. Together, these processes maintain alignment between natural-language narratives and structured knowledge, establishing a framework where reasoning, learning, and collaboration converge.

In the KGTWIN project, one of the work packages will design a language-model-based pipeline able to extract structured knowledge from unstructured text while keeping users aware of the extraction process and its uncertainties.

This work package aims to develop principled methods for extracting RDF knowledge from free text under the guidance of a predefined ontology. The goal is to ensure semantic fidelity, ontological compliance, and traceability of the extracted triples. It builds on the emergence of generative models guided by explicit semantic constraints. Language Models (LMs) can produce rich relational information from unstructured text, but they remain prone to hallucinations, schema violations, and reasoning errors. Conversely, traditional rule-based and supervised extraction systems offer strong guarantees of correctness but are costly to maintain and brittle when applied to new domains. This work package investigates how to combine symbolic knowledge with the language models, to obtain the best of both worlds: scalable extraction, but still traceable. The goal is to systematically evaluate extraction accuracy and recall according to the target ontologies and thesauri, the chosen model, and the pipeline used. The work package will produce metrics and visualization interfaces to expose what is extracted, what is missing, extraction confidence and highlight potential semantic conflicts with the current KG.

Main activities

The PhD subject is about “extracting from and verbalizing RDF to text to support collaborative co-editing of wikis and their corresponding linked data” with the core questions:

• Methods to establish SHACL shapes describing targeted graph patterns, including domain and range restrictions, property cardinalities, and integrity constraints. The method should help define the formal targets that will guide knowledge extraction, starting from ontologies and targeted texts.
• Methods exploiting targeted graph patterns in providing training and validation means for the extraction task. We envision a hybrid pipeline that combines traditional knowledge representation and reasoning techniques and language model-based generation for extracting knowledge graphs from texts. Extracted triples will be verified using the targeted graph patterns and other techniques to ensure that they are compliant with the knowledge graph being built and are entailed by the source text, thereby mitigating hallucinations while maintaining high recall.
• Verbalization techniques capable of transforming RDF subgraphs into fluent natural-language consistent with the ontology semantics. These verbalizations make the entire process explainable to users and can be directly reinserted as editable text within collaborative documents, closing the co-evolution loop between text and structured knowledge.

Skills

• Technical skills and level required : expertise in knowledge graphs, linked data, semantic Web, machine learning, natural language processing, neuro-symbolic appraoches, etc.
• Languages : English and French
• Relational skills : team player, open source community player
• Other valued qualities : humour, kindness and open-mindedness