Exploitation du corpus Enquêtes sociolinguistiques à Orléans (ESLO) par les outils du traitement automatique des langues et de la géomatique

Abstract

The work presented here focuses on the exploitation of the ESLO oral corpus (Enquêtes sociolinguistiques à Orléans, “Sociolinguistic Surveys in Orleans”). This corpus is especially relevant for the digital spatial humanities because it is conducted by linguists from Orléans among the inhabitants of their city. The corpus is processed using Natural Language Processing (NLP) and geomatics tools to extract information about space and its perception in order to represent it on a map of the city.

Keywords

• spatial digital humanities
• linguistics
• oral corpus
• natural language processing
• annotation
• geographic information system