Natural Language Processing in Azure

What is Natural Language Processing?

Natural language processing (NLP) is the area of AI that deals with creating software that understands written and spoken language.

NLP enables you to create software that can:

  • Analyze text documents to extract key phrases and recognize entities (such as places, dates, or people).
  • Perform sentiment analysis to determine how positive or negative the language’s usage in a document is.
  • Interpret spoken language, and synthesize speech responses.
  • Automatically translate spoken or written phrases between languages.
  • Interpret commands and determine appropriate actions.

NLP in Azure:

Text Analytics:


This service usage to analyze text documents and extract key phrases, detect entities (such as places, dates, and people), and evaluate sentiment (how positive or negative a document is)

Unstructured data (images, audio, video, and mostly text) differs from structured data (whole numbers, statistics, spreadsheets, and databases), in that it doesn’t have a set format or organization. It must first be organized, so that it may be analyzed with machine learning techniques. That’s where text analysis tools come in.

Text analysis is a machine learning technique that allows companies to automatically extract and classify text data, such as tweets, emails, support tickets, product reviews, and survey responses.

Translator Text:

This service usage to translate text between more than 60 languages. It investigates the use of software to translate text or speech from one language to another. Mechanical substitution of words in one language for words in another is performed by MT on basic level.

Current machine translation software often allows for domain customization, improving output . This technique is particularly effective in domains where formulaic language is used. It follows that machine translation of legal documents more readily produces usable output than conversation text.

Improved output quality can be made by human intervention: for example, some systems are able to translate more accurately if the user has identified which words in the text are legal names. With the help of these techniques, MT has proven useful as a tool to assist human translators.


This service usage to recognize and synthesize speech, and to translate spoken languages. It is a subfield of computational linguistics that deals with technologies to allow spoken input into systems.

In natural speech there seems limited pauses between successive words, and thus speech segmentation is an important subtask of speech recognition . In most spoken languages, the sounds recollecting successive letters mould into each other , so the conversion of the analog signal to discrete can be a tough process. People are speaking words in the same language with numerous accents, the speech recognition software must be able to get through the wide variety of input as being identical to each other.

Language Understanding:

This service usage to train a language model that can understand spoken or text-based commands. It is a subfield of linguistics that help machines interpret speech or text based commands. In artificial intelligence it deals with machine learning reading comprehension.