Centre dedocumentation
scientifique

ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network / Qinjun Qiu in Transactions in GIS, vol 26 n° 3 (May 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 3 (May 2022) . - pp 1256 - 1279 Titre : ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network Type de document : Article/Communication Auteurs : Qinjun Qiu, Auteur ; Zhong Xie, Auteur ; Shu Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1256 - 1279 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] apprentissage profond [Termes IGN] Chine [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données issues des réseaux sociaux [Termes IGN] échantillonnage de données [Termes IGN] OpenStreetMap [Termes IGN] reconnaissance automatique [Termes IGN] répertoire toponymique [Termes IGN] site wiki [Termes IGN] toponyme Résumé : (auteur) Toponym recognition is used to extract toponyms from natural language texts, which is a fundamental task of ubiquitous geographic information applications. Existing toponym recognition methods with state-of-the-art performance mainly leverage supervised learning (i.e., deep-learning-based approaches) with parameters learned from massive, labeled datasets that must be annotated manually. This is a great inconvenience when model training needs to fit different domain texts, especially those of social media messaging. To address this issue, this article proposes a weakly supervised Chinese toponym recognition (ChineseTR) architecture that leverages a training dataset creator that generates training datasets automatically based on word collections and associated word frequencies from various texts and an extension recognizer that employs a basic bidirectional recurrent neural network based on particular features designed for toponym recognition. The results show that the proposed ChineseTR achieves a 0.76 F1 score in a corpus with a 0.718 out-of-vocabulary rate and a 0.903 in-vocabulary rate. All comparative experiments demonstrate that ChineseTR is an effective and scalable architecture that recognizes toponyms. Numéro de notice : A2022-462 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.12902 Date de publication en ligne : 02/02/2022 En ligne : https://doi.org/10.1111/tgis.12902 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100796 [article]

The effect of map label language on the visual search of cartographic point symbols / Paweł Cybulski in Cartography and Geographic Information Science, vol 49 n° 3 (May 2022)  

Public [article]  inCartography and Geographic Information Science > vol 49 n° 3 (May 2022) . - pp 189 - 204 Titre : The effect of map label language on the visual search of cartographic point symbols Type de document : Article/Communication Auteurs : Paweł Cybulski, Auteur ; Vassilios Krassanakis, Auteur Année de publication : 2022 Article en page(s) : pp 189 - 204 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] détection de cible [Termes IGN] étiquette [Termes IGN] langage cartographique [Termes IGN] langue [Termes IGN] lecture de carte [Termes IGN] oculométrie [Termes IGN] sémiologie graphique [Termes IGN] symbole graphique [Termes IGN] visualisation cartographique [Vedettes matières IGN] Cartologie Résumé : (auteur) The present study aims to examine how the visual search for cartographic symbols is affected by the language of map labels. More specifically, we explore the influence of native language in the performance of a visual search map task which is referred to target point symbol detection. The main research hypothesis is that the relative position of the target symbols plays a significant role in the visual search process, although labels language impacts reaction time. In a controlled laboratory experiment with 38 participants and eye tracking technology, we used maps with labels in participants’ native language (Polish) and in Chinese, which participants could neither read nor write. We find that the detection of target symbols with Chinese labels is faster when the symbol’s location is peripheral. On the other hand, faster detection of target symbols with labels in participants’ native language favors central location. It turned out that having noticed the target symbol, participants fixated on the native language label. For Chinese labels, having seen the target symbol, participants did not fixate on the label. It also turned out that when participants searched for a target symbol located in the peripheral zone, more visual attention was in this zone. However, when the target symbol’s location was central, the participants’ visual attention focused mostly on the central zone. This confirms the significant role of the location of cartographic symbols in the visual search process. Numéro de notice : A2022- 292 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2021.2007419 Date de publication en ligne : 16/12/2021 En ligne : https://doi.org/10.1080/15230406.2021.2007419 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100340 [article]

GazPNE: annotation-free deep learning for place name extraction from microblogs leveraging gazetteer and synthetic data by rules / Xuke Hu in International journal of geographical information science IJGIS, vol 36 n° 2 (February 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 2 (February 2022) . - pp 310 - 337 Titre : GazPNE: annotation-free deep learning for place name extraction from microblogs leveraging gazetteer and synthetic data by rules Type de document : Article/Communication Auteurs : Xuke Hu, Auteur ; Hussein S. Al-Olimat, Auteur ; Jens Kersten, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 310 - 337 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] apprentissage profond [Termes IGN] classification hybride [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données topographiques [Termes IGN] extraction de données [Termes IGN] géobalise [Termes IGN] microblogue [Termes IGN] OpenStreetMap [Termes IGN] répertoire toponymique [Termes IGN] toponyme [Termes IGN] Twitter Résumé : (auteur) Extracting precise location information from microblogs is a crucial task in many applications, particularly in disaster response, revealing where damages are, where people need assistance, and where help can be found. A crucial prerequisite to location extraction is place name extraction. In this paper, we present GazPNE: a hybrid approach to place name extraction which fuses rules, gazetteers, and deep learning techniques without requiring any manually annotated data. The core of the approach is to learn the intrinsic characteristics of multi-word place names with deep learning from gazetteers. Specifically, GazPNE consists of a rule-based system to select n-grams from the microblogs that potentially contain place names, and a C-LSTM model that decides if the selected n-gram is a place name or not. The C-LSTM is trained on 388.1 million examples containing 6.8 million positive examples with US and Indian place names extracted from OpenStreetMap and 381.3 million negative examples synthesized by rules. We evaluate GazPNE against the SoTA on a manually annotated 4,500 tweet dataset which contains 9,026 place names from three foods: 2016 in Louisiana (US), 2016 in Houston (US), and 2015 in Chennai (India). GazPNE achieves SotA performance on the test data with an F1 of 0.84. Numéro de notice : A2022-164 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.1947507 Date de publication en ligne : 07/07/2021 En ligne : https://doi.org/10.1080/13658816.2021.1947507 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99787 [article]

Generating geographical location descriptions with spatial templates: a salient toponym driven approach / Mark M. Hall in International journal of geographical information science IJGIS, vol 36 n° 1 (January 2022)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 36 n° 1 (January 2022) . - pp 55 - 85 Titre : Generating geographical location descriptions with spatial templates: a salient toponym driven approach Type de document : Article/Communication Auteurs : Mark M. Hall, Auteur ; Christopher B. Jones, Auteur Année de publication : 2022 Article en page(s) : pp 55 - 85 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Toponymie [Termes IGN] image Flickr [Termes IGN] OpenStreetMap [Termes IGN] relation spatiale [Termes IGN] répertoire toponymique [Termes IGN] saillance [Termes IGN] toponyme [Termes IGN] traitement du langage naturel Résumé : (auteur) Natural language descriptions of geographical locations are used frequently in daily life and there is a motivation to create systems that generate such descriptions automatically, for purposes such as documentation of where events have taken place, where a person is located, where photos were taken and where plants and animals are located. Typically location descriptions combine references to named geographical features with vague spatial relational terms, such as near, north of and at that relate locations to the features. Here we describe a system for generating location descriptions, that combines spatial templates, that model the applicability of different spatial relations relative to a reference location, with toponyms in the vicinity of the described location that are selected according to aspects of salience. The toponyms are retrieved from a gazetteer service based on OpenStreetMap for which we create a hierarchical feature classification scheme to facilitate selection of toponyms according to distinctiveness of their feature types and other aspects of salience. The advantages of the approach are demonstrated in a user study, relative to an existing state of the art system and to other baseline approaches that include manually created captions and the automated methods of two widely used photo captioning systems. Numéro de notice : A2022-043 Affiliation des auteurs : non IGN Thématique : TOPONYMIE Nature : Article DOI : 10.1080/13658816.2021.1913498 Date de publication en ligne : 28/04/2021 En ligne : https://doi.org/10.1080/13658816.2021.1913498 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99402 [article]

Deep learning for toponym resolution: Geocoding based on pairs of toponyms / Jacques Fize in ISPRS International journal of geo-information, vol 10 n° 12 (December 2021)  

Public [article]  inISPRS International journal of geo-information > vol 10 n° 12 (December 2021) . - n° 818 Titre : Deep learning for toponym resolution: Geocoding based on pairs of toponyms Type de document : Article/Communication Auteurs : Jacques Fize, Auteur ; Ludovic Moncla , Auteur ; Bruno Martins, Auteur Année de publication : 2021 Article en page(s) : n° 818 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Toponymie [Termes IGN] analyse de groupement [Termes IGN] apprentissage profond [Termes IGN] échantillonnage [Termes IGN] géocodage [Termes IGN] matrice de co-occurrence [Termes IGN] site wiki [Termes IGN] toponyme [Termes IGN] zone d'intérêt Résumé : (auteur) Geocoding aims to assign unambiguous locations (i.e., geographic coordinates) to place names (i.e., toponyms) referenced within documents (e.g., within spreadsheet tables or textual paragraphs). This task comes with multiple challenges, such as dealing with referent ambiguity (multiple places with a same name) or reference database completeness. In this work, we propose a geocoding approach based on modeling pairs of toponyms, which returns latitude-longitude coordinates. One of the input toponyms will be geocoded, and the second one is used as context to reduce ambiguities. The proposed approach is based on a deep neural network that uses Long Short-Term Memory (LSTM) units to produce representations from sequences of character n-grams. To train our model, we use toponym co-occurrences collected from different contexts, namely textual (i.e., co-occurrences of toponyms in Wikipedia articles) and geographical (i.e., inclusion and proximity of places based on Geonames data). Experiments based on multiple geographical areas of interest—France, United States, Great-Britain, Nigeria, Argentina and Japan—were conducted. Results show that models trained with co-occurrence data obtained a higher geocoding accuracy, and that proximity relations in combination with co-occurrences can help to obtain a slightly higher accuracy in geographical areas with fewer places in the data sources. Numéro de notice : A2021-927 Affiliation des auteurs : non IGN Thématique : TOPONYMIE Nature : Article DOI : 10.3390/ijgi10120818 Date de publication en ligne : 02/12/2021 En ligne : https://doi.org/10.3390/ijgi10120818 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99293 [article]

A semantics-based approach for simplifying IFC building models to facilitate the use of BIM models in GIS / Junxiang Zhu in Remote sensing, vol 13 n° 22 (November-2 2021)  

Permalink

Famous charts and forgotten fragments: exploring correlations in early Portuguese nautical cartography / Bruno Almeida in International journal of cartography, vol 7 n° 1 (March 2021)  

Permalink

Shedding light on typical species: implications for habitat monitoring / Gianmaria Bonari in Plant sociology, vol 58 n° 1 ([01/02/2021])  

Permalink

Décider du nom d'un lieu / Commission nationale de toponymie (2021)  

Permalink

Definition of the map / Miljenko Lapaine (2021)  

Permalink

Méthodes et outils pour l’analyse spatiale exploratoire en géolinguistique : contributions aux humanités numériques spatialisées / Clément Chagnaud (2021)  

Permalink

Participer à la construction de la base de données des toponymes maritimes du SHOM / Solenn Tual (2021) 

Permalink

Place names in Spanish republican life stories: spatial patterns in locations and perceptions / Laurence Jolivet (2021)  

Permalink

Sherloc: a knowledge-driven algorithm for geolocating microblog messages at sub-city level / Laura Di Rocco in International journal of geographical information science IJGIS, vol 35 n° 1 (January 2021)  

Permalink

Spatial dataset search: Building a dedicated knowledge graph / Mehdi Zhral (2021)  

Permalink