摘要：A new technique to produce a summary of an original text investigated in this paper. The system develops manyapproaches to solve this problem that gave a high quality result. The model consists of four stages. The preprocess stagesconvert the unstructured text into structured. In first stage, the system removes the stop words, pars the text and assigning thePOS (tag) for each word in the text and store the result in a table. The second stageis toextract the important keyphrases inthe text by implementing a new algorithm through ranking the candidate words. The system usestheextractedkeywords/keyphrases toselect theimportant sentence.Each sentencerankeddepending on many features such as the existenceof the keywords/keyphrase in it, the relation between the sentence and the title by using a similarity measurementand othermanyfeatures. The Third stage of the proposed system is to extract the sentences with the highest rank.TheForthstage isthefilteringstage.This stagereducedthe amount of thecandidatesentencesin the summaryin order to produce a qualitativesummaryusingKFIDF measurement.
关键词：Text Summarization; Keyphrase Extraction; Text mining; Data Mining; Text compression
