Document semantic profile definition

Nowadays many users browse Internet by means of search engines, among millions of web records, with the aim of finding specific documents. How do identify documents according to their needs? It makes necessary to find a correct way of extracting relevant information about documents and representing them as metadata. Natural Language Processing (NLP) technologies are required for automatic extracting document information to set specific metadata attributes. These attributes would be NLP tasks outputs like: Headline generation, Topic identification, Sentiment Polarity classification, Document classification, etc., which would form document profiles. In this research we propose to define a document profile, which, as part of an automatic procedure, will serve to semantically meta-classifying documents, initially in both languages English and Spanish.