Textual information in this new era, it is difficult to manually extract the summary of a large data different areas of social communication accumulates the enormous amounts of data. Therefore, it is important to develop methods for searching and absorbing relevant information, selecting important sentences, paragraphs from large texts, to summarize texts by finding topics of the text and frequency based clustering of sentences. In this paper, the author presents some ideas on using mathematical models in presenting the source text into a shorter version with semantics, graph-based approach for text summarization in Mongolian language.