A5019538885- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Topic Modeling
- Manufacturing Process and Optimization
- Text and Document Classification Technologies
- Machine Learning in Bioinformatics
- Spam and Phishing Detection
- Robotic Mechanisms and Dynamics
- Fractal and DNA sequence analysis
- Web Data Mining and Analysis
- Robotic Path Planning Algorithms
- Robot Manipulation and Learning
- Machine Learning and Algorithms
- Algorithms and Data Compression
- Business Strategy and Innovation
- Data Quality and Management
- Fuzzy Logic and Control Systems
- Imbalanced Data Classification Techniques
- Digital Rights Management and Security
- Agriculture and Rural Development Research
- Biomedical Text Mining and Ontologies
- Banking Systems and Strategies
- Advanced Steganography and Watermarking Techniques
- Multi-Agent Systems and Negotiation
- Banking stability, regulation, efficiency
Sorbonne Université
2006
Université Paris Cité
2006
Centre National de la Recherche Scientifique
2006
Département d'Informatique
1995-1999
Caisse des Dépôts et Consignations
1995
This paper presents a method that assists in maintaining rule-based named-entity recognition and classification system. The underlying idea is to use separate system, constructed with the of machine learning, monitor performance training data for second system generated thus avoiding need manual tagging. disagreement two systems acts as signal updating generality approach illustrated by applying it large corpora different languages: Greek French. results are very encouraging, showing this...
This paper shows first the problems raised by proper names in natural language processing. Second, it introduces knowledge representation structure we use based on conceptual graphs. Then explains techniques which are used to process known and unknown names. At last, gives performance of system further works intend deal with.
This paper presents a project, named VIDAR-19, able to extract automatically diseases from the CORD-19 dataset, and also which might be considered as risk factors. The project relies on ICD-11 classification of maintained by WHO. nomenclature is used data source extraction mechanism, repository for results. Developed COVID-19, has ability at calculate relevant indicators. outcome presented in dashboard enables user explore graphically are put back hierarchy. Beyond VIDAR much broader...
For its internal needs as well for commercial purposes, CDC Group has produced several NLP-based on-line contentware applications years. The development process of such is subject to numerous constraints quality service, integration new advances in NLP, direct reactions from users, continuous versioning, short delivery deadlines and cost control. Following this industrial experience, malleability the applications, their openness towards foreign components, efficiency ease exploitation have...
For years, Caisse des Depots et Consignations has produced information filtering applications. To be operational, these applications require high performances which are achieved by using rule-based filters. With this technique, an administrator to tune a set of rules for each topic. However, filters become obsolescent over time. The decrease their is due diachronic polysemy terms that involves loss precision and polymorphism concepts recall. help the maintain his filters, we have developed...
For the TREC-8 routing, one specific filter is built for each topic. Each a classifier trained to recognize documents that are relevant When presented with document, estimates probability document be topic which it has been trained. Since procedure building topic-independent, system fully automatic. By making use of sample have previously evaluated as or not particular topic, term selection performed, and neural network represented by vector frequencies list selected terms. This depends on...
This paper shows first the problems raised by proper names in natural language processing. Second, it introduces knowledge representation structure we use based on conceptual graphs. Then explains techniques which are used to process known and unknown names. At last, gives performance of system further works intend deal with.
With this paper, the authors intended to describe how object-oriented languages have been introduced in banking industry. It shows that there was a need for prototyping management information systems before launching of industrial solutions. Then, it explains rapid adoption paradigms by industry, but also, technical, organisational and human limits they encountered. objects made their come back particularly thanks Internet Java language. At last, paper gives prospective point view on based...