Cette présentation explique une chaîne de traitement complet pour la numérisation et la mise en accès d’environ 11 000 télégrammes diplomatiques du régime de Vichy interceptés par l’Examination Unit canadienne (1941–1945). En combinant reconnaissance optique de caractères par intelligence artificielle (Mistral OCR), extraction automatisée de métadonnées et diffusion en science ouverte via une plateforme Omeka, le projet transforme un corpus archivistique inaccessible en ressource cherchable et réutilisable. Les télégrammes sont désormais librement accessibles, permettant aux chercheurs d’interroger l’ensemble du fonds par recherche plein texte et requêtes booléennes. La contribution examine également les arbitrages techniques, environnementaux et épistémologiques que soulève l’application de méthodes computationnelles aux archives patrimoniales.
", "languages": [ { "id": "fra", "title": { "en": "French" } } ], "publication_date": "2026-05-20", "publisher": "University of Ottawa", "resource_type": { "id": "presentation", "title": { "de": "Pr\u00e4sentation", "en": "Presentation" } }, "rights": [ { "description": { "en": "Permits almost any use subject to providing credit and license notice. Frequently used for media assets and educational materials. The most common license for Open Access scientific publications. Not recommended for software." }, "icon": "cc-by-sa-icon", "id": "cc-by-sa-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by-sa/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution Share Alike 4.0 International" } } ], "subjects": [ { "id": "euroscivoc:49932688", "identifiers": [ { "identifier": "http://data.europa.eu/8mn/euroscivoc/0627c833-88fb-4bbd-86b4-1eb20529fb17", "scheme": "url" } ], "props": { "parents": "euroscivoc:31,euroscivoc:115,euroscivoc:563" }, "scheme": "EuroSciVoc", "subject": "Digital humanities" }, { "id": "mesh:D047789", "scheme": "MeSH", "subject": "World War II" } ], "title": "De l'image au texte cherchable : traitement computationnel des t\u00e9l\u00e9grammes de Vichy (1940-1945)" }, "parent": { "access": { "owned_by": { "user": "420976" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": { "default": "4abebf4f-0213-4cee-8f45-958e968e5ab2", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_submission_policy": "closed", "review_policy": "closed", "visibility": "public" }, "children": { "allow": false }, "created": "2025-09-27T02:14:17.146989+00:00", "custom_fields": { "subjects": [ { "id": "euroscivoc:613" }, { "id": "euroscivoc:939" }, { "id": "euroscivoc:49932688" }, { "id": "mesh:D001109Q000266" } ] }, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "4abebf4f-0213-4cee-8f45-958e968e5ab2", "links": {}, "metadata": { "curation_policy": "", "description": "AI-powered pipeline for transcribing and publishing 13,848 WWII diplomatic telegrams intercepted by Canada (Vichy France & Free French, 1941\u20131945). Datasets, code, and reports are published as open data following FAIR principles.", "organizations": [ { "id": "03c4mmv16" } ], "page": "The Canadian Vichy Intercepts is a digital humanities project that makes publicly accessible a corpus of 13,848 diplomatic telegrams intercepted by the Examination Unit of Canada during World War II. The documents, held on microfilm reels T-17425 to T-17429 at Bibliothèque et Archives Canada, cover Vichy France communications (September 1941 – March 1945) and France libre communications (April 1943 – July 1945). The project develops and documents an AI-powered pipeline using large language model-based OCR (Mistral AI) to transcribe, structure, and extract metadata from the corpus at scale. All outputs — transcriptions, structured datasets, processing code, and performance reports — are published as open data in accordance with FAIR principles. The web interface is accessible via an Omeka Classic platform with IIIF integration at https://omeka.uottawa.ca/examination-unit/. This community archives the project's datasets and code across successive pipeline versions.
", "title": "The Canadian Vichy Intercepts", "type": { "id": "project" }, "website": "https://omeka.uottawa.ca/examination-unit/" }, "revision_id": 7, "slug": "examination-unit", "updated": "2026-04-24T18:29:06.240303+00:00" } ], "ids": [ "4abebf4f-0213-4cee-8f45-958e968e5ab2" ] }, "id": "20342663", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20342663", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20342664", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:20342664", "provider": "oai" } }, "revision_id": 4, "stats": { "all_versions": { "data_volume": 133478745.0, "downloads": 15, "unique_downloads": 13, "unique_views": 19, "views": 19 }, "this_version": { "data_volume": 133478745.0, "downloads": 15, "unique_downloads": 13, "unique_views": 19, "views": 19 } }, "status": "published", "swh": {}, "updated": "2026-05-22T11:18:05.013570+00:00", "versions": { "index": 1, "is_latest": true } }