What is text summarization (preview) in Azure Cognitive Service for Language?

Text summarization is one of the features offered by Azure Cognitive Service for Language, a collection of machine learning and AI algorithms in the cloud for developing intelligent applications that involve written language. Use this article to learn more about this feature, and how to use it in your applications.

This documentation contains the following article types:

• Quickstarts are getting-started instructions to guide you through making requests to the service.
• How-to guides contain instructions for using the service in more specific or customized ways.

Text summarization feature

Text summarization uses extractive text summarization to produce a summary of a document. It extracts sentences that collectively represent the most important or relevant information within the original content. This feature is designed to shorten content that could be considered too long to read. For example, it can condense articles, papers, or documents to key sentences.

As an example, consider the following paragraph of text:

"We�re delighted to announce that Cognitive Service for Language service now supports extractive summarization! In general, there are two approaches for automatic text summarization: extractive and abstractive. This feature provides extractive summarization. Text summarization is a feature that produces a text summary by extracting sentences that collectively represent the most important or relevant information within the original content. This feature is designed to shorten content that could be considered too long to read. Extractive summarization condenses articles, papers, or documents to key sentences."

The text summarization feature would simplify the text into the following key sentences:

Key features

Text summarization supports the following features:

• Extracted sentences: These sentences collectively convey the main idea of the document. They�re original sentences extracted from the input document�s content.
• Rank score: The rank score indicates how relevant a sentence is to a document's main topic. Text summarization ranks extracted sentences, and you can determine whether they're returned in the order they appear, or according to their rank.
• Maximum sentences: Determine the maximum number of sentences to be returned. For example, if you request a three-sentence summary Text summarization will return the three highest scored sentences.
• Positional information: The start position and length of extracted sentences.

Get started with text summarization

To use this feature, you submit raw unstructured text for analysis and handle the API output in your application. Analysis is performed as-is, with no additional customization to the model used on your data. To use text summarization:

Input requirements and service limits

• Text summarization takes raw unstructured text for analysis. See Data and service limits in the how-to guide for more information.
• Text summarization works with a variety of written languages. See language support for more information.

Reference documentation and code samples

As you use text summarization in your applications, see the following reference documentation and samples for Azure Cognitive Services for Language: