Violaine Prince

An NLP-based ontology population for a risk management generic structure

In this paper we propose an NLP-based Ontology Population approach for a Generic Structure instantiation from natural language texts, in the domain of Risk Management. The approach is semi-automatic and based on combined NLP techniques using domain expert intervention for control and validation. It relies on the predicative power of verbs in the instantiation process. It is not domain dependent since it heavily relies on linguistic knowledge. We demonstrate the effectiveness of our method on the ontology of the PRIMA project (supported by the European community) and we populate this generic domain ontology via an available corpus. A first validation of the approach is done through an experiment with Chemical Fact Sheets from Environmental Protection Agency.

Automatic titling of electronic documents with noun phrase extraction

Automatic titling (i.e. providing titles) is one of key domains of Web site accessibility. This paper provides an approach allowing the automatic titling of texts (e.g. emails, fora, etc.) relying on the morphosyntactic study of human written titles in a corpus of various texts. The method is developed in four stages: Corpus acquisition, candidate sentences determination for titling, noun phrase extraction in the candidate sentences, and finally, selecting a particular noun phrase to play the role of the text title (ChTitres approach). The method has been evaluated by ten users, and the satisfaction enquiry shows that the titles selected through this process are relevant.

Semi Automatic Ontology Instantiation in the domain of Risk Management

One of the challenging tasks in the context of Ontological Engineering is to automatically or semi-automatically support the process of Ontology Learning and Ontology Population from semi-structured documents (texts). In this paper we describe a Semi-Automatic Ontology Instantiation method from natural language text, in the domain of Risk Management. This method is composed from three steps 1 ) Annotation with part-of-speech tags, 2) Semantic Relation Instances Extraction, 3) Ontology instantiation process. It’s based on combined NLP techniques using human intervention between steps 2 and 3 for control and validation. Since it heavily relies on linguistic knowledge it is not domain dependent which is a good feature for portability between the different fields of risk management application. The proposed methodology uses the ontology of the PRIMA1 project (supported by the European community) as a Generic Domain Ontology and populates it via an available corpus. A first validation of the approach is done through an experiment with Chemical Fact Sheets from Environmental Protection Agency2.

How can catchy titles be generated without loss of informativeness

Automatic titling of text documents is an essential task for several applications (automatic heading of e-mails, summarization, and so forth). This paper describes a system facilitating information retrieval in a set of textual documents by tackling the automatic titling and subtitling issue. Automatic titling here involves providing both informative and catchy titles. We thus propose two different approaches based on NLP, text mining, and Web Mining techniques. The first one (POSTIT) consists of extracting relevant noun phrases from texts as candidate titles. An original approach combining statistical criteria and noun phrase positions in the text helps in collecting informative titles and subtitles. The second approach (NOMIT) is based on various assumptions made on POSTIT and aims to generate both informative and catchy titles. Both approaches are applied to a corpus of news articles, then evaluated according to two criteria, i.e. informativeness and catchiness.

Knowledge Acquisition Modeling Through Dialogue Between Cognitive Agents

This article tackles learning and communication between cognitive artificial agents. Our focus is on dialogue as the only way for agents to acquire knowledge, as it often happens in natural situations. Since this restriction has scarcely been studied in artificial intelligence (AI) until now; this research aims to provid a dialogue model devoted to knowledge acquisition. It allows two agents, in a “teacher” – “student” relationship, to exchange information with a learning incentive (on behalf of the student). The article first defines the nature of the addressed agents, the types of relation they maintain, and the structure and contents of their knowledge base. It continues by describing the different goals of learning, their realization, and the solutions provided for problems encountered by agents. A general architecture is then established and comment on the part of the theory implementation is given. The conclusion talks about the achievements carried out and the potential improvement of this work.

Modalités de dépistage radiologique devant un risque familial identifié de cancer du sein

Resume L’identification des femmes porteuses d’une mutation genetique ou d’une predisposition genetique suffisamment elevee pour etre assimilee a la premiere categorie, est determinante pour pouvoir induire une modification de la strategie de depistage. Compte tenu du risque cumule de cancer du sein et du vecu tres anxiogene des investigations chez ces patientes, le radiologue se doit d’optimiser le choix des technologies a disposition, le rythme des examens proposes et l’ordre chronologique de leur realisation. Les particularites tumorales et de croissance cellulaire connues chez les patientes mutees vont contribuer a elaborer ces modalites. Au travers des dernieres recommandations nationales publiees, d’une analyse critique de la litterature, de la revue des technologies recentes et des pratiques, les modalites de depistage sont exposees et commentees.

Mining Tweet Data

This paper deals with the quality of textual features in messages in order to classify tweets. The aim of our study is to show how improving the representation of textual data affects the performance of learning algorithms. We will first introduce our method YYYYY. It generalises less relevant words for tweet classification. Secondly we compare and discuss the types of textual features given by different approaches. More precisely we discuss the semantic specificity of textual features, e.g. Named Entity, HashTag.