With the revolution of information available on the internet pages, humans need to extract specific information. This paper presents KEYS (Knowledge Extraction sYStem); an information retrieval and extraction system. It searches for information inside documents represented in UNL, i.e., in semantic hyper-graphs. This allows for retrieval and extraction practices that are language-independent and semantically-oriented. It is expected to provide high-quality knowledge extraction through a shallow analysis of the source text into the Universal Networking Language (UNL) using a specific ontological relations and fully-automatic generation from the resulting UNL document into several different target languages. This is expected to present a novel approach to the topic of identifying the named entity; extracting names with all its types from a natural language form.