Centre de documentation
scientifique

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]

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

Public [article]  inInternational journal of geographical information science IJGIS > vol 32 n° 1-2 (January - February 2018) . - pp 324 - 348 Titre : Toponym matching through deep neural networks Type de document : Article/Communication Auteurs : Rui Santos, Auteur ; Patricia Murrieta-Flores, Auteur ; Pavel Calado, Auteur ; Bruno Martins, Auteur Année de publication : 2018 Article en page(s) : pp 324 - 348 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Toponymie [Termes IGN] appariement [Termes IGN] apprentissage profond [Termes IGN] recherche d'information géographique [Termes IGN] répertoire toponymique [Termes IGN] réseau neuronal artificiel [Termes IGN] similitude sémantique [Termes IGN] toponyme [Termes IGN] traitement de données localisées Résumé : (Auteur) Toponym matching, i.e. pairing strings that represent the same real-world location, is a fundamental problemfor several practical applications. The current state-of-the-art relies on string similarity metrics, either specifically developed for matching place names or integrated within methods that combine multiple metrics. However, these methods all rely on common sub-strings in order to establish similarity, and they do not effectively capture the character replacements involved in toponym changes due to transliterations or to changes in language and culture over time. In this article, we present a novel matching approach, leveraging a deep neural network to classify pairs of toponyms as either matching or nonmatching. The proposed network architecture uses recurrent nodes to build representations from the sequences of bytes that correspond to the strings that are to be matched. These representations are then combined and passed to feed-forward nodes, finally leading to a classification decision. We present the results of a wide-ranging evaluation on the performance of the proposed method, using a large dataset collected from the GeoNames gazetteer. These results show that the proposed method can significantly outperform individual similarity metrics from previous studies, as well as previous methods based on supervised machine learning for combining multiple metrics. Numéro de notice : A2018-027 Affiliation des auteurs : non IGN Thématique : TOPONYMIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2017.1390119 En ligne : https://doi.org/10.1080/13658816.2017.1390119 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89179 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2018011	RAB	Revue	Centre de documentation	En réserve L003	Disponible