A survey on Automatic Text Summarization

Abstract

Text summarization endeavors to produce a summary version of a text, while maintaining the original ideas. The textual content on the web, in particular, is growing at an exponential rate. The ability to decipher through such massive amount of data, in order to extract the useful information, is a major undertaking and requires an automatic mechanism to aid with the extant repository of information. Text summarization systems intent to assist with content reduction by means of keeping the relevant information and filtering the non-relevant parts of the text. In terms of the input, there are two fundamental approaches among text summarization systems. The first approach summarizes a single document. In other words, the system takes one document as an input and produce a summary version as its output. The alternative approach is to take several documents as its input and produce a single summary document as its output. In terms of output, summarization systems are also categorized into two major types. One approach would be to extract exact sentences from the original document in order to build the summary output. The alternative would be a more complex approach, in which the rendered text is a rephrased version of the original document. This paper will offer an in-depth introduction to automatic text summarization. We also mention some evaluation techniques to evaluate the quality of automatic text summarization.