Centre dedocumentation
scientifique

Entry separation using a mixed visual and textual language model: Application to 19th century French trade directories / Bertrand Duménieu (2023)  

Public Titre : Entry separation using a mixed visual and textual language model: Application to 19th century French trade directories Type de document : Article/Communication Auteurs : Bertrand Duménieu , Auteur ; Edwin Carlinet, Auteur ; Nathalie Abadie , Auteur ; Joseph Chazalon, Auteur Editeur : Champs-sur-Marne [France] : Université Gustave Eiffel Année de publication : 2023 Projets : SODUCO / Perret, Julien Importance : 20 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] annuaire [Termes IGN] dix-neuvième siècle [Termes IGN] modèle de langue [Termes IGN] reconnaissance de noms Résumé : (Auteur) When extracting structured data from repetitively organized documents, such as dictionaries, directories, or even newspapers, a key challenge is to correctly segment what constitutes the basic text regions for the target database. Traditionally, such a problem was tackled as part of the layout analysis and was mostly based on visual clues for dividing (top-down) approaches. Some agglomerating (bottom-up) approaches started to consider textual information to link similar contents, but they required a proper over-segmentation of ne-grained units. In this work, we propose a new pragmatic approach whose eciency is demonstrated on 19 th century French Trade Directories. We propose to consider two sub-problems: coarse layout detection (text columns and reading order), which is assumed to be eective and not detailed here, and a ne-grained entry separation stage for which we propose to adapt a state-of-the-art Named Entity Recognition (NER) approach. By injecting special visual tokens, coding, for instance, indentation or breaks, into the token stream of the language model used for NER purpose, we can leverage both textual and visual knowledge simultaneously. Code, data, results and models are available at https://github.com/soduco/ paper-entryseg-icdar23-code, https://huggingface.co/HueyNemud/ (icdar23-entrydetector* variants). Numéro de notice : P2023-002 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE/INFORMATIQUE/TOPONYMIE Nature : Preprint nature-HAL : Préprint DOI : sans Date de publication en ligne : 17/02/2023 En ligne : https://hal.science/hal-03994702v1/ Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102609

The cartography of Kallihirua?: Reassessing indigenous mapmaking and Arctic encounters / Peter R. Martin in Cartographica, vol 57 n° 3 (September 2022)  

Public [article]  inCartographica > vol 57 n° 3 (September 2022) . - pp 239 - 255 Titre : The cartography of Kallihirua?: Reassessing indigenous mapmaking and Arctic encounters Type de document : Article/Communication Auteurs : Peter R. Martin, Auteur Année de publication : 2022 Article en page(s) : pp 239 - 255 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie ancienne [Termes IGN] Arctique [Termes IGN] culture [Termes IGN] dix-neuvième siècle [Termes IGN] ethnologie [Termes IGN] expédition polaire [Termes IGN] Groenland [Termes IGN] histoire de la cartographie [Termes IGN] représentation géographique [Termes IGN] société savante Résumé : (auteur) This article examines a cartographic encounter that took place in 1850 between Kallihirua, a member of Inughuit community of Northern Greenland, and members of the British Admiralty. Drawing on recent literatures that critically assess histories of indigenous mapping, the article explores the troubling circumstances that surrounded this encounter and analyses two maps which were produced as a result. Informed by ongoing debates pertaining to the decolonization of geographical knowledge, the article also reflects critically upon the extent to which historical indigenous cosmologies were commensurate with non-indigenous cartographic traditions and thus reassesses the motivations that lay behind the production and circulation of these maps. The article thus concludes by arguing that while Kallihirua certainly did contribute various types of geographical knowledge during this encounter, to label him as the sole author of these maps would be a problematic act of "cartographic ventriloquism". Numéro de notice : A2022-851 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3138/cart-2021-0012 Date de publication en ligne : 04/11/2022 En ligne : https://doi.org/10.3138/cart-2021-0012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102089 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
031-2022031	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Genome-wide evolutionary response of European oaks during the Anthropocene / Dounia Saleh in Evolution letters, vol 6 n° 1 (February 2022)  

Public [article]  inEvolution letters > vol 6 n° 1 (February 2022) . - pp 4 - 20 Titre : Genome-wide evolutionary response of European oaks during the Anthropocene Type de document : Article/Communication Auteurs : Dounia Saleh, Auteur ; Jun Chen, Auteur ; Jean-Charles Leple, Auteur ; Thibault Leroy, Auteur ; Laura Truffaut, Auteur ; Benjamin Dencausse, Auteur ; Céline Lalanne, Auteur ; Karine Labadie, Auteur ; Isabelle Lesur, Auteur ; Didier Bert, Auteur ; Frédéric Lagane, Auteur ; François Morneau , Auteur ; Jean-Marc Aury, Auteur ; Christophe Plomion, Auteur ; Martin Lascoux, Auteur ; Antoine Kremer, Auteur Année de publication : 2022 Projets : 3-projet - voir note / Perret, Julien Article en page(s) : pp 4 - 20 Note générale : bibliographie This research was supported by the European Research Council through an Advanced Grant (project TREEPEACE # FP7-339728), by France Génomique (project EVOL-OAK, ANR-10-INBS-09-08), and by the French Forest Service (ONF) (INRAE-ONF TREEPEACE contract). Langues : Anglais (eng) Descripteur : [Termes IGN] dix-huitième siècle [Termes IGN] dix-neuvième siècle [Termes IGN] France (géographie physique) [Termes IGN] génétique forestière [Termes IGN] Quercus sessiliflora [Termes IGN] vingt-et-unième siècle [Termes IGN] vingtième siècle [Vedettes matières IGN] Botanique Résumé : (auteur) The pace of tree microevolution during Anthropocene warming is largely unknown. We used a retrospective approach to monitor genomic changes in oak trees since the Little Ice Age (LIA). Allelic frequency changes were assessed from whole-genome pooled sequences for four age-structured cohorts of sessile oak (Quercus petraea) dating back to 1680, in each of three different oak forests in France. The genetic covariances of allelic frequency changes increased between successive time periods, highlighting genome-wide effects of linked selection. We found imprints of parallel linked selection in the three forests during the late LIA, and a shift of selection during more recent time periods of the Anthropocene. The changes in allelic covariances within and between forests mirrored the documented changes in the occurrence of extreme events (droughts and frosts) over the last 300 years. The genomic regions with the highest covariances were enriched in genes involved in plant responses to pathogens and abiotic stresses (temperature and drought). These responses are consistent with the reported sequence of frost (or drought) and disease damage ultimately leading to the oak dieback after extreme events. They provide support for adaptive evolution of long-lived species during recent climatic changes. Although we acknowledge that other sources (e.g., gene flow, generation overlap) may have contributed to temporal covariances of allelic frequency changes, the consistent and correlated response across the three forests lends support to the existence of a systematic driving force such as natural selection. Numéro de notice : A2022-076 Affiliation des auteurs : IGN+Ext (2020- ) Thématique : BIODIVERSITE/FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1002/evl3.269 Date de publication en ligne : 05/01/2022 En ligne : https://doi.org/10.1002/evl3.269 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99572 [article]

A benchmark of named entity recognition approaches in historical documents : application to 19th century French directories / Nathalie Abadie (2022)  

Public Titre : A benchmark of named entity recognition approaches in historical documents : application to 19th century French directories Type de document : Article/Communication Auteurs : Nathalie Abadie , Auteur ; Edwin Carlinet, Auteur ; Joseph Chazalon, Auteur ; Bertrand Duménieu , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2022 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 13237 Projets : SODUCO / Perret, Julien Conférence : DAS 2022, 5th IAPR International Workshop on Document Analysis Systems 22/05/2022 25/05/2022 La Rochelle France Proceedings Springer Importance : pp 445 - 460 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dix-neuvième siècle [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] exploration de texte [Termes IGN] objet géohistorique [Termes IGN] reconnaissance de noms [Termes IGN] traitement du langage naturel Résumé : (auteur) Named entity recognition (NER) is a necessary step in many pipelines targeting historical documents. Indeed, such natural language processing techniques identify which class each text token belongs to, e.g. “person name”, “location”, “number”. Introducing a new public dataset built from 19th century French directories, we first assess how noisy modern, off-the-shelf OCR are. Then, we compare modern CNN- and Transformer-based NER techniques which can be reasonably used in the context of historical document analysis. We measure their requirements in terms of training data, the effects of OCR noise on their performance, and show how Transformer-based NER can benefit from unsupervised pre-training and supervised fine-tuning on noisy data. Results can be reproduced using resources available at https://github.com/soduco/paper-ner-bench-das22 and https://zenodo.org/record/6394464. Numéro de notice : C2022-030 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1007/978-3-031-06555-2_30 En ligne : http://dx.doi.org/10.1007/978-3-031-06555-2_30 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101088

Connecting family trees to construct a population-scale and longitudinal geo-social network for the U.S. / Caglar Koylu in International journal of geographical information science IJGIS, vol 35 n° 12 (December 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 12 (December 2021) . - pp 2380 - 2423 Titre : Connecting family trees to construct a population-scale and longitudinal geo-social network for the U.S. Type de document : Article/Communication Auteurs : Caglar Koylu, Auteur ; Diansheng Guo, Auteur ; Yuan Huang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2380 - 2423 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] appariement sémantique [Termes IGN] collecte de données [Termes IGN] démographie [Termes IGN] dix-neuvième siècle [Termes IGN] données localisées des bénévoles [Termes IGN] données publiques [Termes IGN] Etats-Unis [Termes IGN] généalogie [Termes IGN] géocodage [Termes IGN] historique des données [Termes IGN] itération [Termes IGN] migration humaine [Termes IGN] mobilité humaine [Termes IGN] réseau social géodépendant [Termes IGN] système d'information historique Résumé : (auteur) We collected 92,832 user-contributed and publicly available family trees from rootsweb.com, including 250 million individuals who were born in North America and Europe between 1630 and 1930. We cleaned and connected the family trees to create a population-scale and longitudinal family tree dataset using a workflow of data collection and cleaning, geocoding, fuzzy record linkage and a relation-based iterative search for connecting trees and deduplication of records. Given the largest connected component of nearly 40 million individuals, and a total of 80 million individuals, we generated, to date, the largest population-scale and longitudinal geo-social network over centuries. We evaluated the representativeness of the family tree dataset for historical population demography and mobility by comparing the data to the 1880 Census. Our results showed that the family trees were biased towards males, the elderly, farmers, and native-born white segments of the population. Individuals were highly mobile – in our 1880 sample of parent-child pairs where both were born in the U.S., 47% were born in different states. Our findings agreed with prior studies that people migrated from East to West in horizontal bands, and the trend was reflected in the dialects and regional structure of the U.S. Numéro de notice : A2021-876 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1821885 Date de publication en ligne : 30/09/2020 En ligne : https://doi.org/10.1080/13658816.2020.1821885 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99139 [article]

Analyzing routes in Ottoman Greater Syria using historical GIS: The 1849 Saida map / Motti Zohar in Transactions in GIS, vol 25 n° 5 (October 2021)  

Permalink

The accuracy of urban maps in Spain through GIS: The example of Burgos from the nineteenth to the twentieth century / Barbara Polo-Martin in Cartographica, vol 56 n° 3 (Fall 2021)  

Permalink

Genome-wide evolutionary response of European oaks since the Little Ice Age / Dounia Saleh (2021)  

Permalink

Le parallèle des Pyrénées / Yves Maugard (2021)

Permalink

Can we characterize river corridor evolution at a continental scale from historical topographic maps? A first assessment from the comparison of four countries / J. Horacio Garcia in River Research and Applications, vol 36 n° 6 (July 2020)  

Permalink

Multi-century reconstruction suggests complex interactions of climate and human controls of forest fire activity in a Karelian boreal landscape, North-West Russia / N. Ryzhkova in Forest ecology and management, vol 459 (1 March 2020)  

Permalink

Quels plans de comparaison à Paris avant le nivellement général de la France ? / Alain Coulomb in XYZ, n° 162 (mars 2020)

Permalink

Spatial visualization of quantitative landscape changes in an industrial region between 1827 and 1883. Case study Katowice, southern Poland / Paweł Cybulski in Journal of maps, vol 16 n° 1 ([02/01/2020])  

Permalink

Mapping urban fingerprints of odonyms automatically extracted from French novels / Ludovic Moncla in International journal of geographical information science IJGIS, vol 33 n° 12 (December 2019)  

Permalink

The transformation of relief representation on topographic maps in Hungary: from hachures to contour lines / Lazlo Zentai in Cartographic journal (the), vol 55 n° 2 (May 2018)  

Permalink