Team Orpailleur

Overall Objectives
Scientific Foundations
Application Domains
New Results
Other Grants and Activities

Section: Software

Knowledge-Based Systems and Semantic Web


Keywords : knowledge discovery from databases, text mining, frequent itemset search, association rule extraction, information retrieval, navigation, semantic web.

Participants : Emmanuel Nauer [ contact person ] , Yannick Toussaint.

The “CreChainDo” second system makes use of FCA for information retrieval on the web. Many recent systems use FCA for improving the access to documents on the web. Among them, the Credo system [72] , [73] , uses a concept lattice to reorganize the list of documents returned by a search engine as an answer to a given query. In Credo, a lattice is built according to the title and the snippet of each documents returned by Google. Navigating into the lattice hierarchy guides the access to the web documents.

In this way, a lattice contains concepts that are relevant and some others that are not relevant for a given information retrieval task. Extending the Credo approach, we introduce lattices into an interactive and iterative system, called CreChainDo (major [8] ). The CreChainDo system uses FCA for reorganizing the list of documents returned by Google according a lattice. The lattice, presented as a tree-hierarchy, helps the user to explore the search results in a structured and synthetic way. The CreChainDo system offers to the user a way of expressing a negative or positive agreement with some concept of the lattice, in agreement with the objective of information retrieval. These user choices are converted into extension or reduction operations on the lattice, in order to make the lattice evolve and to better fit his/her needs.

The Kasimir System for Decision Knowledge Management

Keywords : classification-based reasoning, case-based reasoning, edition and maintenance of knowledge, decision knowledge management, semantic portal.

Participants : Fadi Badra, Julien Cojan, Jean Lieber [ contact person ] , Amedeo Napoli, Thomas Meilender.

The objective of the Kasimir system is decision support and knowledge management for the treatment of cancer. A number of modules have been developed within the Kasimir system for editing of treatment protocols, visualization, and maintenance. Actually, two versions of Kasimir are currently used. A first version is based on an ad hoc object-based representation formalism. A second version is developed within a semantic portal, based on OWL and extensions of OWL, implying the development of the two user interfaces, namely EdHibou and NavHibou [76] . The instance editor EdHibou is used for querying the protocols represented within the Kasimir system. The browser NavHibou is developed for navigating in the class hierarchies built by a reasoner based on OWL. Moreover, since the Kasimir inference engine is based on subsumption, a study on the integration of an extended inference engine taking into account inferences based on CBR, and on an integration within the semantic web, is under study.

The software CabamakA for case base mining for adaptation knowledge acquisition is a module of the Kasimir system [12] . This system performs case base mining for adaptation knowledge acquisition and provides information units to be used for building adaptation rules [75] . Actually, the mining process in CabamakA is implemented thanks to a frequent close itemset extraction module of the Coron platform (see § 5.1.1 ). The adaptation knowledge acquisition process is not fully automated: an analyst guides CabamakA, following the principles of knowledge discovery, i.e. the analyst filters and interprets the results of the mining process, to be rewritten into adaptation rules.

Taaable: a system for retrieving and creating new cooking recipes by adaptation

Keywords : text mining, knowledge acquisition, ontology engineering, semantic annotation, case-based reasoning, hierarchical classification.

Participants : Fadi Badra, Julien Cojan, Jean Lieber [ contact person ] , Thomas Meilender, Amedeo Napoli, Emmanuel Nauer, Yannick Toussaint.

Taaable is a system whose objectives are to retrieve textual cooking recipes and to adapt these retrieved recipes whenever needed. Suppose that someone is looking for a “leek pie” but has only an “onion pie” recipe: how can the onion pie recipe be adapted?

The Taaable system combines principles, methods, and technologies of knowledge engineering, namely CBR, ontology engineering, text mining, text annotation, knowledge representation, and hierarchical classification [35] . Ontologies for representing knowledge about the cooking domain, and a terminological base for binding texts and ontology concepts, have been built from textual web resources. These resources are used by an annotation process for building a formal representation of textual recipes. A CBR engine considers each recipe as a case, and uses domain knowledge for reasoning, especially for adapting an existing recipe w.r.t. constraints provided by the user, holding on ingredients and dish types.

The Taaable system is available on line at . This system has been designed with the collaboration of the SILEX team (LIRIS Lyon) and the RCLN team (LIPN Paris 13). In addition, Taaable won the second price in the first “Computer Cooking Contest” [69] (European Conference on Case-Based Reasoning, September 2008, Trier, Germany), and in the second “Computer Cooking Contest” (International Conference on Case-Based Reasoning, July 2009, Seattle, USA) [35] .


Logo Inria