Natural Language Processing Method for Multilingual Semantic Indexing

National audienceThis paper deal with multilingual document indexing. We propose an indexing method based on natural language processing techniques. First of all, the most important term of the document are extracted using general characteristics of language and statistical methods. Thus, term extracting stages can be applied to any document whatever the document language is. Secondly, our indexing method uses multilingual ontology in order to find the most relevant concepts representing the document content. Our method can be applied to multilingual corpus containing document written in different languages; This indexing procedure is part of a multilingual document system and untitled SyDoM, that manage XML document