DALiH - Digitizing Armenian Linguistic Heritage

Université Sorbonne Paris Nord; France; Sur place; EUR 40 000 - 50 000; Plein temps

Résumé du poste

A prestigious university in France is seeking a Postdoctoral Researcher or Research Engineer for a 9-month contract focused on the digitization of Armenian linguistic heritage. Ideal candidates will hold a Master's or PhD in relevant fields and possess strong skills in machine learning and deep learning. The role involves research on dialectal variability, analysis of heritage documents, and the use of large language models. This position is based at LIPN in Villetaneuse.

Qualifications

• Experience in machine learning and deep learning is essential.
• Candidate should have a strong academic background in relevant fields.

Responsabilités

• Conduct research on dialectal variability and linguistic similarity.
• Analyze heritage documents and extract information.
• Utilize large language models for annotation tasks.

Connaissances

Machine learning

Deep learning

Natural Language Processing

Formation

Master’s degree (M2) or PhD in computer science or related fields

Outils

PyTorch

JAX

Description du poste

Organisation/Company Université Sorbonne Paris Nord Research Field Computer science » Informatics Mathematics Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Country France Application Deadline 10 Dec 2025 - 00:00 (UTC) Type of Contract Temporary Job Status Full-time Offer Starting Date 1 Jan 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Postdoc.

Call for Applications – Postdoctoral Researcher / Research Engineer (ANR DALiH).

LIPN – CNRS / Université Sorbonne Paris Nord.

The Laboratoire d’Informatique de Paris-Nord (LIPN, UMR 7030 CNRS – Université Sorbonne Paris Nord) is recruiting a postdoctoral researcher or research engineer for a 9-month fixed-term contract, ideally starting in December 2025 or January 2026, as part of the ANR DALiH project on the digitization of Armenian linguistic heritage.

Research Topics

• Dialectal variability and linguistic similarity: modeling dialectal diversity in low-resource languages (notably Armenian), building robust representations (embeddings, inter-variety alignment), detecting and quantifying dialect proximity/distance, and evaluating the impact of this variability on natural language processing tasks.
• Analysis of heritage documents; information extraction in contexts with complex reading order, including logical segmentation, structuring, post-correction, and text normalization.
• Large Language Models for annotation tasks and zero-shot evaluation in linguistic analysis.

Profile

• Master’s degree (M2) or PhD in computer science, NLP, machine learning, deep learning, or a related field.
• Strong experience in machine learning and deep learning (PyTorch or JAX).

Environment

The position is based at LIPN (Villetaneuse), within the RCLN team (Knowledge Representation and Natural Language), with partners at INALCO and the École Nationale des Chartes – PSL.

Application

• CV (including publication list).
• References and/or examples of work (preprints, GitHub repository).

Contact: [e-mail]

Laboratory: Laboratoire d'Informatique de Paris Nord