Centre dedocumentation
scientifique

Comparing supervised learning algorithms for Spatial Nominal Entity recognition / Amine Medad (2020)  

Public Titre : Comparing supervised learning algorithms for Spatial Nominal Entity recognition Type de document : Article/Communication Auteurs : Amine Medad, Auteur ; Mauro Gaio, Auteur ; Ludovic Moncla, Auteur ; Sébastien Mustière , Auteur ; Yannick Le Nir, Auteur Editeur : Göttingen : Copernicus publications Année de publication : 2020 Collection : AGILE GIScience Series num. vol 1 Projets : 1-Pas de projet / Conférence : AGILE 2020, 23rd AGILE Conference on Geographic Information Science 16/06/2020 19/06/2020 Chania - Crète Grèce Open Access Proceedings Importance : 18 p. Format : 21 x 30 cm Note générale : biblographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes descripteurs IGN] algorithme d'apprentissage [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] entité géographique [Termes descripteurs IGN] recherche d'information géographique [Termes descripteurs IGN] reconnaissance de noms [Termes descripteurs IGN] traitement du langage naturel Résumé : (auteur) Discourse may contain both named and nominal entities. Most common nouns or nominal mentions in natural language do not have a single, simple meaning but rather a number of related meanings. This form of ambiguity led to the development of a task in natural language processing known as Word Sense Disambiguation. Recognition and categorisation of named and nominal entities is an essential step for Word Sense Disambiguation methods. Up to now, named entity recognition and categorisation systems mainly focused on the annotation, categorisation and identification of named entities. This paper focuses on the annotation and the identification of spatial nominal entities. We explore the combination of Transfer Learning principle and supervised learning algorithms, in order to build a system to detect spatial nominal entities. For this purpose, different supervised learning algorithms are evaluated with three different context sizes on two manually annotated datasets built from Wikipedia articles and hiking description texts. The studied algorithms have been selected for one or more of their specific properties potentially useful in solving our problem. The results of the first phase of experiments reveal that the selected algorithms have similar performances in terms of ability to detect spatial nominal entities. The study also confirms the importance of the size of the window to describe the context, when word-embedding principle is used to represent the semantics of each word. Numéro de notice : C2020-013 Affiliation des auteurs : LaSTIG+Ext (2020- ) Thématique : GEOMATIQUE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-1-15-2020 date de publication en ligne : 15/07/2020 En ligne : https://doi.org/10.5194/agile-giss-1-15-2020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95688

A natural language processing and geospatial clustering framework for harvesting local place names from geotagged housing advertisements / Yingjie Hu in International journal of geographical information science IJGIS, Vol 33 n° 3-4 (March - April 2019)  

Public [article]  inInternational journal of geographical information science IJGIS > Vol 33 n° 3-4 (March - April 2019) . - pp 714 - 738 Titre : A natural language processing and geospatial clustering framework for harvesting local place names from geotagged housing advertisements Type de document : Article/Communication Auteurs : Yingjie Hu, Auteur ; Huina Mao, Auteur ; Grant McKenzie, Auteur Année de publication : 2019 Article en page(s) : pp 714 - 738 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Toponymie [Termes descripteurs IGN] analyse de groupement [Termes descripteurs IGN] information sémantique [Termes descripteurs IGN] publicité [Termes descripteurs IGN] recherche d'information géographique [Termes descripteurs IGN] reconnaissance de noms [Termes descripteurs IGN] répertoire toponymique [Termes descripteurs IGN] toponymie locale [Termes descripteurs IGN] traitement du langage naturel Résumé : (Auteur) Local place names are frequently used by residents living in a geographic region. Such place names may not be recorded in existing gazetteers, due to their vernacular nature, relative insignificance to a gazetteer covering a large area (e.g. the entire world), recent establishment (e.g. the name of a newly-opened shopping center) or other reasons. While not always recorded, local place names play important roles in many applications, from supporting public participation in urban planning to locating victims in disaster response. In this paper, we propose a computational framework for harvesting local place names from geotagged housing advertisements. We make use of those advertisements posted on local-oriented websites, such as Craigslist, where local place names are often mentioned. The proposed framework consists of two stages: natural language processing (NLP) and geospatial clustering. The NLP stage examines the textual content of housing advertisements and extracts place name candidates. The geospatial stage focuses on the coordinates associated with the extracted place name candidates and performs multiscale geospatial clustering to filter out the non-place names. We evaluate our framework by comparing its performance with those of six baselines. We also compare our result with four existing gazetteers to demonstrate the not-yet-recorded local place names discovered by our framework. Numéro de notice : A2019-213 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1458986 date de publication en ligne : 13/04/2018 En ligne : https://doi.org/10.1080/13658816.2018.1458986 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92685 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2019032	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
079-2019031	SL	Revue	Centre de documentation	Revues en salle	Disponible

Retrieving relevant land cover and land use data to study urban climate change / Bénédicte Bucher (2019)

Public Titre : Retrieving relevant land cover and land use data to study urban climate change Type de document : Article/Communication Auteurs : Bénédicte Bucher , Auteur ; Marie-Dominique Van Damme , Auteur ; Stephane Garcia, Auteur Editeur : Leibniz : Leibniz Institute of Ecological Urban and Regional Development Année de publication : 2019 Projets : URCLIM / Masson, Valéry Conférence : ILUS 2019 International land use symposium 04/12/2019 06/12/2019 Paris France programme sans actes Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes descripteurs IGN] changement climatique [Termes descripteurs IGN] climat urbain [Termes descripteurs IGN] image Landsat [Termes descripteurs IGN] métadonnées géographiques [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] pertinence [Termes descripteurs IGN] plateforme collaborative [Termes descripteurs IGN] recherche d'information géographique [Termes descripteurs IGN] spécification [Termes descripteurs IGN] spécification de processus [Termes descripteurs IGN] utilisation du sol Résumé : (auteur) The study of urban local phenomena related to climate, like heat islands, road icing, streets overflow during high precipitation events or air pollution, is necessary to develop efficient adaptation strategies to climate change. The URCLIM project studies more specifically urban climate knowledge production and services design. It is funded by the "European Research Area for Climate Services" that targets "the user-driven development, translation and transfer of climate knowledge to researchers and decision—makers in policy and business [..] as well as guidance in the use of climate knowledge." Climate scientists model interactions between meteorological phenomena (wind, moisture, temperature) described at a given scale and the surface of earth described at a finer scale in order to calculate finer meteorological phenomena, e.g. temperature variations depending on trees in cities. The climate community designs such generic canopy models adapted for a set of similar places. To obtain land data required to feed these canopy models, instead of each team producing ad hoc land data on his experimental site, this community has developed a joint approach: 1) agree on common formal specifications of such land models, also known as Local climate Zones, 2) design a production procedure of such Local climate zones data affordable by the community itself. The World Urban Database and Access Portal Tools, WUDAPT support collaborative production of Local climate Zones level 0 (resolution from 500m to 1km) based on Landsat satellite imagery. Producing Local climate Zones level 1 (50 to 100 meters), requires other sources related to buildings and vegetation (Masson et al. 2019). This requires discovering and reusing heterogeneous spatial data whereas there is neither one search engine nor a set of well identified catalogues that can be searched with user-oriented query words. This presentation will concentrate firstly on analyzing what are the relevance criteria from the urban climate scientist perspective to retrieve an existing urban land model or to produce it. We consider for example an accessibility criterion as well as an extrapolation criterion. Second we review the contribution of available metadata and ontologies to make proper recommendations to this scientist who wishes to design an urban land model for his specific study. Important metadata are: features catalogues, spatial and temporal coverage, temporal, geometric and semantic resolutions and accuracies. Last we demonstrate a metadata curation process based on the URCLIM infolab, a collaborative metadata platform (Bucher and Van Damme 2018). Numéro de notice : C2019-066 Affiliation des auteurs : LaSTIG COGIT (2012-2019) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComSansActesPubliés-Unpublished DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97021

Une IDS, oui, mais pour quoi faire ? / Anonyme in Géomatique expert, n° 125 (novembre - décembre 2018)

Public [article]  inGéomatique expert > n° 125 (novembre - décembre 2018) . - pp 17 - 21 Titre : Une IDS, oui, mais pour quoi faire ? Type de document : Article/Communication Auteurs : Anonyme, Auteur Année de publication : 2018 Article en page(s) : pp 17 - 21 Langues : Français (fre) Descripteur : [Vedettes matières IGN] Infrastructure de données [Termes descripteurs IGN] données localisées [Termes descripteurs IGN] recherche d'information géographique [Termes descripteurs IGN] système d'information géographique Résumé : (Auteur) La mode est aux IDS, les infrastructures de données géographiques. Que ce soit au niveau régional ou au niveau intercommunal, les initiatives se multiplient pour offrir aux utilisateurs d’information géographique des guichets uniques d’accès. Mais pas que. Numéro de notice : A2018-624 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92915 [article]

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
IFN-001-P002099	PER	Revue	Nogent-sur-Vernisson	Salle périodiques	Exclu du prêt

Extraction of spatio‐temporal data about historical events from text documents / Susanna Abraham in Transactions in GIS, vol 22 n° 3 (June 2018)  

Public [article]  inTransactions in GIS > vol 22 n° 3 (June 2018) . - pp 677 - 696 Titre : Extraction of spatio‐temporal data about historical events from text documents Type de document : Article/Communication Auteurs : Susanna Abraham, Auteur ; Stephan Mäs, Auteur ; Lars Bernard, Auteur Année de publication : 2018 Article en page(s) : pp 677 - 696 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes descripteurs IGN] base de données historiques [Termes descripteurs IGN] histoire [Termes descripteurs IGN] recherche d'information géographique [Termes descripteurs IGN] Time-geography [Termes descripteurs IGN] traitement du langage naturel Résumé : (Auteur) Often, we are faced with questions regarding past events and the answers are hidden in the historical text archives. The growing developments in geographic information retrieval and temporal information retrieval techniques have given new ways to explore digital text archives for spatio‐temporal data. The question is how to retrieve the answers from the text documents. This work contributes to a better understanding of spatio‐temporal information extraction from text documents. Natural language processing techniques were used to develop an information extraction approach using the GATE language processing software. The developed framework uses gazetteer matching, spatio‐temporal relationship extraction and pattern‐based rules to recognize and annotate elements in historical text documents. The extracted spatio‐temporal data is used as input for GIS studies on the time–geography context of the German–Herero resistance war of 1904 in Namibia. Related issues when analyzing the historical data in current GIS are discussed. Particularly problematic are movement data in small scale with poor temporal density and trajectories that are short or connect very distant locations. Numéro de notice : A2018-577 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12448 date de publication en ligne : 17/08/2018 En ligne : https://doi.org/10.1111/tgis.12448 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92324 [article]

Are prominent mountains frequently mentioned in text? Exploring the spatial expressiveness of text frequency / Curdin Derungs in International journal of geographical information science IJGIS, vol 32 n° 5-6 (May - June 2018)  

Permalink

An approach to measuring semantic relatedness of geographic terminologies using a thesaurus and lexical database sources / Zugang Chen in ISPRS International journal of geo-information, vol 7 n° 3 (March 2018)  

Permalink

Generating vague neighbourhoods through data mining of passive web data / Paul Brindley in International journal of geographical information science IJGIS, vol 32 n° 3-4 (March - April 2018)  

Permalink

Geographic information retrieval method for geography mark-up language data / Caili Fang in ISPRS International journal of geo-information, vol 7 n° 3 (March 2018)  

Permalink

Geospatial data on the web / Linda Van Den Brink (2018)    

Permalink

Toponym matching through deep neural networks / Rui Santos in International journal of geographical information science IJGIS, vol 32 n° 1-2 (January - February 2018)  

Permalink

Reference data enhancement for geographic information retrieval using linked data / Tiago H. V. M. Moura in Transactions in GIS, vol 21 n° 4 (August 2017)  

Permalink

Aggregation-based information retrieval system for geospatial data catalogs / Javier Lacasta in International journal of geographical information science IJGIS, vol 31 n° 7-8 (July - August 2017)  

Permalink

Classifying natural-language spatial relation terms with random forest algorithm / Shihong Du in International journal of geographical information science IJGIS, vol 31 n° 3-4 (March-April 2017)  

Permalink

Cross-domain image localization by adaptive feature fusion / Neelanjan Bhowmik (2017)  

Permalink