Local cultural heritage document repositories are characterized by contents strongly attached to a territory (i.e. geographical references). The user must be able to consider such repositories according to a focus, which takes into account his/her geographical interests, and which allows one to access the relevant document's contents from a geographical point of view. This paper presents the Virtual Itineraries in the Pyrenees (PIV) project. Spatial and temporal core models are proposed to give a formal representation of geographical information. The models take into account the characteristics of heterogeneous human modes of expression: written language and captures of drawings, maps, pictures, etc. Semantic processes have been built to automatically manage the spatial and temporal information from non-structured data. A ''back office'' prototype, which adds these processes to classic information extraction (IE) approaches, while associating a geographical information retrieval (GIR) service is proposed. This service searches for any links between formal representations of geographic information in document collections, and similar representations in a user's information query. Finally, the paper presents the design work, giving the details of the principles of result visualization and navigation, while proposing a ''front office'' first implementation of the system.

A global process to access documents' contents from a geographical point of view

This paper presents the Virtual Itineraries in Pyrenees (PIV) project. Spatial and temporal unified models are proposed to give a formal representation to geographical information. The aim is to improve the access to local cultural and heritage document collections. The models take into account characteristics of heterogeneous human expression modes: written language and captures of drawings, maps, pictures, etc. Semantic treatments have been built to automatically manage spatial and temporal information from non-structured data. These treatments are added to classical information extraction (IE) approaches. Then, geographical information retrieval processing is based on geographical information systems (GIS) algorithms. These algorithms look for any relations between formal representations of geographic information in documents collections and similar representations in a user query. Finally we propose a prototype implementing such geographic IE and geographic Information Retrieval (IR).

Geographical information access for non-structured data

By presenting the LinguaStream platform, we introduce different methodological principles and analysis models, which make it possible to build hybrid experimental NLP systems by articulating corpus processing tasks.

/pdf/linguastream-an-integrated-environment-for-computational-4f7j23mtc5.pdf

LinguaStream: an integrated environment for computational linguistics experimentation

This paper deals with spatial Information Extraction (IE) and Retrieval (IR) in Digital Libraries environments. The proposed approach (implemented within PIV(1) prototype) is based on a linguistic and semantic analysis of digital corpora and free text queries. First, we present requirements and a methodology of semantic annotation for automatic indexing and geo-referencing of text documents. Then we report on a case study where the spatial-based IR process is evaluated and compared to classical (statistical-based) IR approaches using first pure spatial queries and then more general ones dealing with both spatial and thematic scopes. The main result in these first experiments shows that combining a spatial approach with a classical (statistical-based) IR one improves in a significant way retrieval accuracy, namely in the case of general queries.

Towards an IE and IR System Dealing with Spatial Information in Digital Libraries - Evaluation Case Study

Notre travail s'insere dans la problematique de l'acces a l'information spatiale presente dans des corpus textuels territoriaux. Nous proposons d'aller au-dela des systemes de recherche d'information classiques bases sur l'analyse statistique des documents, peu adaptes pour ce cas particulier, via un traitement linguistique cible interpretant l'information spatiale. Notre hypothese est que des traitements relativement peu couteux suffisent a degager l'essentiel de l'information. Ils sont un bon point de depart pour une interpretation plus poussee par la suite, utilisant les proprietes geographiques de l'information extraite afin de developper un systeme d'indexation a plusieurs niveaux d'abstraction. Nous proposons en effet une methode de recherche d'information spatiale multi-niveaux indexant un corpus textuel brut. Cette methode qui extrait l'information d'un corpus et l'interprete, permet d'ameliorer l'efficacite de systemes de recherche d'information a chaque fois que l'interrogation comporte une connotation spatiale. L'interpretation permet en outre de retrouver le contexte dans lequel l'information spatiale a ete utilisee. En particulier, elle permet d'indexer des unites de texte en leur associant des contextes de type itineraire, description locale ou comparaison de lieux.

/pdf/plate-forme-pour-l-indexation-spatiale-multi-niveaux-d-un-52pi9wxqit.pdf

Plate-forme pour l'indexation spatiale multi-niveaux d'un corpus territorialisé

This paper deals with indexation of multi-modal geographic documents by the mean of two constructs: geographic entities, and their semantic relations. These relations concern more specifically contrast or similarity between the entities with regard to the described phenomenon. Geographic entities are retrieved in both text and maps using proper analysis techniques. Contrast or similarity relations -- identified as discursive structures in the text and as semiologic facts in the map -- are then characterised by dedicated modules. The model induced by these constructs offers semantic indexing and querying possibilities. It also provides a valuable basis for collaborative interpretation of individual components of the multi-modal document. The whole system is deployed in a distributed environment, made interoperable by use of major web standards.

Éric Faurot

Papers

Multimodal indexation of contrastive structures in geographical documents