Important note – AWS Application Services for AI/ML – MLS-C01 Study Guide

Important note

It is a best practice not to overprovision your function’s timeout settings. Always understand your code performance and set a function timeout accordingly. Overprovisioning a function timeout results in Lambda functions running longer, causing unexpected costs. If you are using asynchronous API calls in your Lambda function, then it is good to write them into SNS topics on success and trigger another Lambda function from that. If it needs human intervention, then it is suggested that you use AWS Step Functions.

In this section, you learned and applied Amazon Transcribe to convert speech into text. In the next section, you will learn about one of the most powerful AWS AI services you can use to get the maximum amount of insight from our text data.

Implementing natural language processing with Amazon Comprehend

This service helps you extract insights from unstructured text. Unstructured text information is growing exponentially. A few data source examples are as follows:

  • Customer engagement: Call center, issue triage, customer surveys, and product reviews
  • Business processes: Customer/vendor emails, product support messages, and operation support feedback
  • Records and research: Whitepapers and medical records
  • News and social media: Social media analytics, brand trends, and correlated events

Now, the question is, what can you do with this data? How can you analyze it and extract any value out of it? The answer is Amazon Comprehend, which is used to get insights from unstructured data.

Some common uses of Amazon Comprehend include the following:

  • Information management system
  • More accurate search system on organized topics
  • Sentiment analysis of users
  • Support ticket classification
  • Language detection from a document and then translating it into English using Amazon Translate
  • Creating a system to label unstructured clinical data to assist in research and analysis purposes
  • Extracting topics from saved audio files of company meetings or TV news

Next, you’ll explore the benefits of Amazon Comprehend.

Exploring the benefits of Amazon Comprehend

Some of the advantages of using Comprehend can be seen in the following image:

Figure 8.14 – A block diagram showing Amazon Comprehend’s capabilities

Let’s look at these in more detail:

  • It detects the language of the text and extracts key phrases. Amazon Comprehend can be used for sentiment analysis and topic modeling too.
  • Amazon Comprehend Medical can be used to extract medical information.
  • You pay for what you use since this is a fully managed service; you do not have to pay for the infrastructure. You do not need to train, develop, and deploy your own model.
  • The topic modeling service works by extracting up to 100 topics. A topic is a keyword bucket so that you can see what is in the actual corpus of documents.
  • It is accurate, continuously trained, and easy to use.

Next, you’ll get hands-on with Amazon Comprehend.