Research Internship: Span and Arc Representations for Relation Extraction

About the role

The AOC team at LIPN is seeking a motivated Master’s student to join a research internship focused on developing span and arc representations for relation extraction. The project aims to reduce waste in the fresh‑food supply chain, using data from the Rungis Market.

Key responsibilities

• Design and implement models that capture span‑based and arc‑based features for relation extraction tasks.
• Collect, preprocess, and annotate data related to food supply‑chain operations.
• Evaluate model performance on real‑world waste‑reduction scenarios.
• Collaborate with the Califrais partner to align research outcomes with industry needs.
• Document experiments, results, and contribute to scientific publications.

Required profile

• Enrolled in a Master’s program (M2 level) in Computer Science, Data Science, or a related field.
• Strong interest in natural language processing and machine learning research.
• Ability to work independently and within a multidisciplinary team.

Required skills

• Experience with Python programming.
• Familiarity with machine‑learning libraries (e.g., PyTorch, TensorFlow, scikit‑learn).
• Basic knowledge of NLP concepts such as tokenization, embeddings, and relation extraction.

What we offer

• Hands‑on research experience on a real‑world sustainability challenge.
• Mentorship from senior researchers at LIPN and industry experts at Califrais.
• Opportunity to co‑author scientific papers and present findings.