Arij Sediri

mXS : Automatic Annotation System (for French) / Data Mining and Named Entity Recognition system During 6 months, I have designed, exprimented, implemented and evaluated a named entity recognition system that leverage automatically extracted annotation rules (using pattern mining). Besides annotation, this system also allows to view and manipulate patterns (sequential, hierarchical) that are correlated to so-called markers (currently, XML tags). mXS allows to annotate Named Entities in French texts by using a model learned over the Etape corpora, a french TreeBank that has already been annotated with part-of-speech tags.

Project : Quaero Quaero is a European research and development program with the goal of developing multimedia and multilingual indexing and management tools for professional and general public applications (such as search engines). - Named Entity Recognition - Construction and Use of Language Resources - Data Mining and Named Entity Recognition system

As innovative construction company specialized in Short-Text Classification and Analysis, and in partnership with several research universities, Succeed Together exploits the potential of language processing to develop collective performance. Project : Meeting Software / Conferencing Software Meeting Software can analyze ultra rapidly answers of an unlimited number of participants in open-ended questions. The Conferencing Software deals ultra rapidly with participants’ answers by producing a rich and easily exploitable synthesis of all responses thanks to semantic grouping. - Short-Text Classification and Analysis - Semantic Analysis - Integrated Learning / Semi Supervised Learning - Statistical Analysis of Structured and Unstructured Data - Text Classification / Lexical and Textual Mapping - Machine Learning for Textual Data Analysis - Information Retrieval and Information Extraction