Catherine Comparot

An easy way of expressing conceptual graph queries from keywords and query patterns

Our goal is to hide the complexity of formulating a query expressed in a graph query language such as conceptual graphs. We propose a mechanism for querying a collection of documents previously annotated by means of conceptual graphs. Our queries are based on keywords given by the user. Our system associates the keywords with their corresponding concepts. Then it selects a set of patterns which are pre-written typical queries. The patterns are instantiated according to the initial keywords. Finally, the user can modify the pre-written query he/she selects in order to fit his/her initial needs as well as possible. The query graph obtained is projected into the annotation graphs associated with the documents. The documents which answer the query are returned to the user.

A semi-automatic approach for building ontologies from acollection of structured web documents

Many collections of structured documents are available on the web. The collection generally describes the characteristics of entities from a single type, where each page describes one entity. These documents are adequate knowledge sources for building ontologies. As they benefit from a strong and shared layout, they contain less well written text than plain text files but their architecture is very meaningful. Classical linguistic-based methods for identifying concepts and relations are no longer appropriate for analyzing them.The approach we propose in this paper exploits various properties of such documents, combining layout/formatting analysis and linguistic analysis, and using semantic annotation.

Conceptual Graphs and Ontologies for Information Retrieval

We propose a mechanism for annotating and querying document collections based on the semantic modeling of the context of a search. We model on the one hand the topics concerned by the content of the document and on the other hand the metadata associated with the documents, by means of two ontologies expressed in the conceptual graph model. The semantic annotating mechanism is done by automatically building conceptual graphs.

Semantic Integration of Geospatial Data from Earth Observations

We propose an approach to semantically enrich metadata records of satellite imagery with external data. As a result we are able the identify relevant images using a larger set of matching criteria. Conventional methods for annotating data sets are usually based on metadata records (with attributes such as title, provider, access mode, and spatio-temporal characteristics), which offer a narrow view of the world. Enriching metadata with contextual information (e.g., the region depicted in the image has been recently affected by extreme weather) requires formalizing spatio-temporal relationships between metadata records and external data sources. Semantic technologies play a key role in such scenarios by providing an infrastructure based on RDF and ontologies.