In recent years, digital technology in the social sciences and humanities has become an
indispensable element in the archiving process, enabling better preservation and enhancement
of heritage. This thesis proposes to enhance the value of the heritage collections of the
Bourgogne Franche-Comté region by identifying the actors and places.
The aim of this work is to produce data and tools for archival mining, for example to trace the personal
history of an individual, an organization, a business, etc., to the
for example to trace the personal history of an individual, an organisation, a business, etc. at the
on a regional scale. This data will be usable via online navigation interfaces,
allowing the user to link information from heterogeneous sources and thus produce new
knowledge.
The EMONTAL project is fully in line with axis 1 "Sciences, languages, textualities" of the CRIT laboratory (EA
3224), and in particular in sub-axis 2, which aims to develop models and methodologies for
methodologies aiming at the understanding, generation and automatic representation of textual contents
including textual semantics.
The objective of the EMONTAL project is to propose a methodology to automatically process documentary and archive collections of heterogeneous natures
(newspapers, chronicles, administrative documents, reports, etc.) for the purpose of heritage enhancement dedicated to a given socio-historical context.
historical context. This is based on the development of textual analyses, which fall within the field of Automatic Language Processing
and discourse analysis.
The tools and data produced will be made available to the general public but also to documentalists, researchers and actors of the socio-economic fabric of the region, in order to facilitate the valorisation of these funds.
The tools and data produced will be made available to the general public, but also to documentalists, researchers and players in the socio-economic fabric of the region, in order to facilitate the valorisation of these collections. This work will constitute a technological base
for future projects, thus enhancing research activity in the Bourgogne Franche-Comté region.
iana.atanassova@univ-fcomte.fr
Gutehrlé, N. (2024). Semantic Search in Archive Collections Through Interpretable and Adaptable Relation Extraction About Person and Places. In N. Goharian, N. Tonellotto, Y. He, A. Lipani, G. McDonald, C. Macdonald & I. Ounis (Éd.), Advances in Information Retrieval (p. 315-318). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-56069-9_37
Gutehrlé, N., & Atanassova, I. (2023). Comprendre les archives : vers de nouvelles interfaces de recherche reposant sur l’annotation sémantique des documents Understanding Archives : Towards New Research Interfaces Relying on the Semantic Annotation of Documents. CiDE.23 : Document et archivage : pratiques formelles et informelles. https://hal.science/hal-04523110 https://hal.science/hal-04523110
Gutehrlé, N., Doucet, A., & Jatowt, A. (2022). Archive TimeLine Summarization (ATLS): Conceptual Framework for Timeline Generation over Historical Document Collections. Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, 13-23. https://aclanthology.org/2022.latechclfl-1.3 https://aclanthology.org/2022.latechclfl-1.3/
Gutehrlé, N., & Atanassova, I. (2022). Processing the structure of documents: Logical Layout Analysis of historical newspapers in French. Journal of Data Mining & Digital Humanities, NLP4DH. https://doi.org/10.46298/jdmdh.9093 https://jdmdh.episciences.org/9614/pdf
Gutehrlé, N., & Atanassova, I. (2021). Logical Layout Analysis Applied to Historical Newspapers. Proceedings of the Workshop on Natural Language Processing for Digital Humanities, 85-94. https://aclanthology.org/2021.nlp4dh-1.10 https://aclanthology.org/2021.nlp4dh-1.10/
Gutehrlé, N., & Atanassova, I. (2021). Dataset for Logical-layout analysis on French historical newspapers (Version 1.0). Zenodo. https://doi.org/10.5281/zenodo.5752440 https://doi.org/10.5281/zenodo.5752440
Gutehrlé, N., Harlamov, O., Karimi, F., Wei, H., Jean-Caurant, A., & Pivovarova, L. (2021). SpaceWars: A Web Interface for Exploring the Spatio-temporal Dimensions of WWI Newspaper Reporting. HistoInformatics 2021 – 6th International Workshop on Computational History. https://ceur-ws.org/Vol-2981/paper3.pdf