What is summarization?

Important

Conversation summarization is only available using:

  • REST API
  • Python
  • C#

Summarization is a feature offered by Azure AI Language, a combination of generative Large Language models and task-optimized encoder models that offer summarization solutions with higher quality, cost efficiency, and lower latency. Use this article to learn more about this feature, and how to use it in your applications.

Out of the box, the service provides summarization solutions for three types of genre, plain texts, conversations, and native documents. Text summarization only accepts plain text blocks. Conversation summarization accepts conversational input, including various speech audio signals. Native document summarization accepts documents in their native formats, such as Word, PDF, or plain text. For more information, see Supported document formats.

Capabilities

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.

Key features for conversation summarization

Conversation summarization supports the following features:

  • Recap: Summarizes a conversation into a brief paragraph.
  • Issue/resolution summarization: Call center specific features that give a summary of issues and resolutions in conversations between customer-service agents and your customers.
  • Chapter title summarization: Segments a conversation into chapters based on the topics discussed in the conversation, and gives suggested chapter titles of the input conversation.
  • Narrative summarization: Generates detail call notes, meeting notes or chat summaries of the input conversation.

As an example, consider the following example conversation:

Agent: "Hello, you're chatting with Rene. How may I help you?"

Customer: "Hi, I tried to set up wifi connection for Smart Brew 300 espresso machine, but it didn't work."

Agent: "I'm sorry to hear that. Let's see what we can do to fix this issue. Could you push the wifi connection button, hold for 3 seconds, then let me know if the power light is slowly blinking?"

Customer: "Yes, I pushed the wifi connection button, and now the power light is slowly blinking."

Agent: "Great. Thank you! Now, please check in your Contoso Coffee app. Does it prompt to ask you to connect with the machine?"

Customer: "No. Nothing happened."

Agent: "I see. Thanks. Let's try if a factory reset can solve the issue. Could you please press and hold the center button for 5 seconds to start the factory reset."

Customer: "I've tried the factory reset and followed the above steps again, but it still didn't work."

Agent: "I'm very sorry to hear that. Let me see if there's another way to fix the issue. Please hold on for a minute."

Conversation summarization feature would simplify the text as follows:

Example summary Remark Conversation aspect
Customer is unable to set up wifi connection for Smart Brew 300 espresso machine a customer issue in a customer-and-agent conversation issue
The agent suggested several troubleshooting steps, including checking the wifi connection, checking the Contoso Coffee app, and performing a factory reset. However, none of these steps resolved the issue. The agent then put the customer on hold to look for another solution. solutions tried in a customer-and-agent conversation resolution
The customer contacted the agent for assistance with setting up a wifi connection for their Smart Brew 300 espresso machine. The agent guided the customer through several troubleshooting steps, including a wifi connection check, checking the power light, and a factory reset. Despite following these steps, the issue persisted. The agent then decided to explore other potential solutions Summarizes a conversation into one paragraph recap
Troubleshooting SmartBrew 300 Espresso Machine Segments a conversation and generates a title for each segment; usually cowork with narrative aspect chapterTitle
The customer is having trouble setting up a wifi connection for their Smart Brew 300 espresso machine. The agent suggests several solutions, including a factory reset, but the issue persists. Segments a conversation and generates a summary for each segment, usually cowork with chapterTitle aspect narrative

Get started with summarization

To use summarization, you submit for analysis and handle the API output in your application. Analysis is performed as-is, with no added customization to the model used on your data. There are two ways to use summarization:

Development option Description Links
REST API Integrate conversation summarization into your applications using the REST API. Quickstart: Use conversation summarization

Input requirements and service limits

  • Conversation summarization takes structured text for analysis. For more information, see data and service limits.
  • Conversation summarization works with various spoken languages. For more information, see language support.

Reference documentation and code samples

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

Development option / language Reference documentation Samples
C# C# documentation C# samples
Java Java documentation Java Samples
JavaScript JavaScript documentation JavaScript samples
Python Python documentation Python samples