Automatic Summarization

Why Trust Techopedia

What Does Automatic Summarization Mean?

Automatic summarization is the process by a which computer program creates a shortened version of text.

Advertisements

The product of the process contains the most important points from the original text. Search engines such as Google use automatic summarization to produce key phrase extractions in search results.

Techopedia Explains Automatic Summarization

Automatic summarization helps to reduce large text documents to a short set of words or a paragraph that conveys the meaning of the full text.

There are two methods used in automatic summarization:

  1. The extractive method selects a subset of existing words, phrases or sentences in the original text to form summaries.
  2. The abstractive method builds an internal semantic representation and uses natural language generation techniques to create summaries that resembles the ones created by humans. This summary may have words that are not present in the original document.

There are also two main types of automatic summarization:

  1. Key-phrase extraction selects individual words or phrases to tag documents.
  2. Document summarization selects whole sentences to create short paragraph summaries.

Technologies that produce coherent summaries of any type must take document length, writing style and syntax into account to make useful summaries.

Advertisements

Related Terms

Margaret Rouse
Technology Expert
Margaret Rouse
Technology Expert

Margaret is an award-winning technical writer and teacher known for her ability to explain complex technical subjects to a non-technical business audience. Over the past twenty years, her IT definitions have been published by Que in an encyclopedia of technology terms and cited in articles by the New York Times, Time Magazine, USA Today, ZDNet, PC Magazine, and Discovery Magazine. She joined Techopedia in 2011. Margaret's idea of a fun day is helping IT and business professionals learn to speak each other’s highly specialized languages.