One of the major tasks of the Natural language processing is automatic summarization. Automatic summarization is the process of reducing a text document with a computer program in order to create a summary that retains the most important points of the original document. Generally, there are two approaches to automatic summarization: extraction and abstraction. Extractive methods work by selecting a subset of existing words, phrases, or sentences in the original text to form the summary. Abstractive methods build an internal semantic representation.We would like to show you an example of how the summarization works. We have chosen Martin Luther King's speech "I have a dream" (a 17 min. video ) and made a summarization using the extraction method.We got the following six sentences as a summary:"When the architects of our republic wrote the magnificent words of the Constitution and the Declaration of Independence, they were signing a promissory note to which every American was to fall heir. I have a dream that one day on the red hills of Georgia, the sons of former slaves and the sons of former slave owners will be able to sit down together at the table of brotherhood. I have a dream that one day, down in Alabama, with its vicious racists, with its governor having his lips dripping with the words of "interposition" and "nullification" - one day right there in Alabama little black boys and black girls will be able to join hands with little white boys and white girls as sisters and brothers. I have a dream that one day every valley shall be exalted, and every hill and mountain shall be made low, the rough places will be made plain, and the crooked places will be made straight; "and the glory of the Lord shall be revealed and all flesh shall see it together.This is our hope, and this is the faith that I go back to the South with. And when this happens, when we allow freedom ring, when we let it ring from every village and every hamlet, from every state and every city, we will be able to speed up that day when all of God's children, black men and white men, Jews and Gentiles, Protestants and Catholics, will be able to join hands and sing in the words of the old Negro spiritual: Free at last! "What do you think about the quality of the summary?There are main steps of the algorithm:getting a raw text; extracting sentences from the text;splitting each sentence into words (tokens);setting a special Weight (kind of measure for importance) per each sentence;sorting sentences by Weight in descending order;taking requested amount of top sentences for summary;sort these top sentences by their natural order, i.e. by the order in source raw text.You can try to summarize any text by your own as there are a lot of online summarization tools: textcompactor, freesummarizer, www.tools4noobs Will you use summary API if we make an open access to it?
