Understand prebuilt capabilities of the Azure AI Language service

• 6 minutes

The Azure AI Language service provides various features for understanding human language. You can use each feature to better communicate with users, better understand incoming communication, or use them together to provide more insight into what the user is saying, intending, and asking about.

Azure AI Language service features fall into two categories: Pre-configured features, and Learned features. Learned features require building and training a model to correctly predict appropriate labels, which is covered in upcoming units of this module.

This unit covers most of the capabilities of the Azure AI Language service, but head over to the Azure AI Language service documentation for a full list, including quickstarts and a full explanation of everything available.

Using these features in your app requires sending your query to the appropriate endpoint. The endpoint used to query a specific feature varies, but all of them are prefixed with the Azure AI Language resource you created in your Azure account, either when building your REST request or defining your client using an SDK. Examples of each can be found in the next unit.

Pre-configured features

The Azure AI Language service provides certain features without any model labeling or training. Once you create your resource, you can send your data and use the returned results within your app.

The following features are all pre-configured.

Summarization

Summarization is available for both documents and conversations, and will summarize the text into key sentences that are predicted to encapsulate the input's meaning.

Named entity recognition

Named entity recognition can extract and identify entities, such as people, places, or companies, allowing your app to recognize different types of entities for improved natural language responses. For example, given the text "The waterfront pier is my favorite Seattle attraction", Seattle would be identified and categorized as a location.

Personally identifiable information (PII) detection

PII detection allows you to identify, categorize, and redact information that could be considered sensitive, such as email addresses, home addresses, IP addresses, names, and protected health information. For example, if the text "email@contoso.com" was included in the query, the entire email address can be identified and redacted.

Key phrase extraction

Key phrase extraction is a feature that quickly pulls the main concepts out of the provided text. For example, given the text "Text Analytics is one of the features in Azure AI Services.", the service would extract "Azure AI Services" and "Text Analytics".

Sentiment analysis

Sentiment analysis identifies how positive or negative a string or document is. For example, given the text "Great hotel. Close to plenty of food and attractions we could walk to", the service would identify that as positive with a relatively high confidence score.

Language detection

Language detection takes one or more documents, and identifies the language for each. For example, if the text of one of the documents was "Bonjour", the service would identify that as French.

Learned features

Learned features require you to label data, train, and deploy your model to make it available to use in your application. These features allow you to customize what information is predicted or extracted.

Conversational language understanding (CLU)

CLU is one of the core custom features offered by Azure AI Language. CLU helps users to build custom natural language understanding models to predict overall intent and extract important information from incoming utterances. CLU does require data to be tagged by the user to teach it how to predict intents and entities accurately.

The exercise in this module will be building a CLU model and using it in your app.

Custom named entity recognition

Custom entity recognition takes custom labeled data and extracts specified entities from unstructured text. For example, if you have various contract documents that you want to extract involved parties from, you can train a model to recognize how to predict them.

Custom text classification

Custom text classification enables users to classify text or documents as custom defined groups. For example, you can train a model to look at news articles and identify the category they should fall into, such as News or Entertainment.

Question answering

Question answering is a mostly pre-configured feature that provides answers to questions provided as input. The data to answer these questions comes from documents like FAQs or manuals.

For example, say you want to make a virtual chat assistant on your company website to answer common questions. You could use a company FAQ as the input document to create the question and answer pairs. Once deployed, your chat assistant can pass input questions to the service, and get the answers as a result.

For a complete list of capabilities and how to use them, see the Azure AI Language documentation.