Microsoft AI School - Natural Language Processing

Microsoft AI school - Diving Into Natural Language Processing

A Simple Introduction to Natural Language Processing in Azure

Natural Language Processing (NLP) is the branch of artificial intelligence (AI) that gives computer programs the ability to see, hear, speak with, and understand human language the way it is written and spoken - referred to as natural language. Some common examples of NLP in practice today are digital assistants, voice-operated GPS systems, speech-to-text dictation softwares, and customer service chatbots.   

Microsoft Azure makes it extremely easy to build applications that support natural language processing by providing numerous text analytics, translation, and language understanding services. Microsoft AI School offers you a curated list of modules and other resources to learn and create applications that use NLP. 

The following learning path in MS AI School will help you to dive into Natural Language Processing in Azure: “Explore natural language processing”. This learning path has four modules. Read ahead to get a quick peek at each module of this learning path. 

Prerequisite: You should be able to navigate the Azure portal to pursue this learning path.

Module1: Analyze Text with The Text Analytics Service

 

Text analytics refers to the ability of an artificial intelligence algorithm to evaluate different attributes of a text to gain specific insights into the contents of that text. A person relies on his/her own experiences and knowledge to gain insights into a text. However, a computer must be provided with similar knowledge so that it can perform the task. This includes certain techniques that can be used to train the application to analyze text. Programming such techniques can often be complex; however, Azure provides you with the Text Analytics cognitive service that simplifies application development with the help of pre-trained models.

Text Analytics is a text-mining AI service in Azure that uncovers insights such as sentiment analysis, entities, relations and key phrases in unstructured text

In the first module, you will learn how to use the Text Analytics cognitive service in Azure to gain insights into unstructured text with the help of pre-trained models that can:

• Determine the language of a document or text.
• Determine a positive or negative sentiment of a text by performing sentiment analysis.
• Extract key phrases from the text that indicate the main idea of the text.
• Identify and categorize entities in the text.

Here’s an overview of the units covered within this module:

Module 2: Recognize and Synthesize Speech

• Speech recognition refers to the ability of an AI system to detect and interpret a spoken input and transcribe it into a text output.
• Speech synthesis refers to the ability of an AI system to generate speech from text. You can consider it as the reverse of speech recognition.

Microsoft Azure features both speech recognition and speech synthesis capabilities through its Speech cognitive service that include the following APIs:

• The Speech-to-Text API
• The Text-to-Speech API

The second module of this learning path will help you learn how to recognize and synthesize speech using Azure Cognitive Services. Thus, the primary objectives of this module are to help you:

• Learn about speech recognition and synthesis
• Learn how to use the Speech cognitive service in Azure

Here’s an overview of the units covered within this module:

Module 3: Translate Text and Speech

• Text translation is the field of AI that translates documents from one language to another. For example, It enables you to translate web pages from one language to another on the web and even provides you with the ability to translate email communications sent by foreign governments.
   
• Speech translation refers to the ability of AI systems to translate between spoken languages. This can be done directly (speech-to-speech translation) and also by translating to an intermediary text format (speech-to-text translation).

Microsoft Azure features cognitive services that facilitate translation. These services are:

• The Translator Text service
• The Speech service

After completing the third module of this learning path, you will be able to perform text and speech translation using Azure Cognitive Services.

Here’s an overview of the units covered within this module:

Module 4: Create a Language Model with Language Understanding

A natural language understanding (NLU) AI service is one that allows users to interact with applications, bots and IoT devices by using natural language.

In the final module of this learning path, you will be introduced to the Language understanding service in Microsoft Azure that can be used to create applications that understand language. Thus the major learning objectives of this module are to help you learn:

• What Language Understanding is.
• Key features of Language Understanding - utterances, entities, and intents.
• Build and publish a natural-language machine-learning model.

Here’s an overview of the units covered within this module:

Conclusion

Thus, if you are looking to master the concepts and dive deep into Natural Language Processing in Azure with the help of real-time examples and exercises, then this learning path will serve as the perfect roadmap for you. You will learn how to implement numerous cognitive services in Azure and build solutions without requiring in-depth knowledge of complex AI algorithms.