Foundry Tool offering natural language processing over existing text, such as sentiment, key phrase extraction, entity recognition, PII detection, summarisation and language detection. Prebuilt features work without training, and nothing new is generated.
Also called Azure AI Language, Text Analytics, Azure AI Language, Text Analytics.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Azure Language in Foundry Tools in context, with comparison tables and the common traps.
Terms in this definition
- Chat message roles
Labels on chat messages: instructions go under system, the person's input under user, the model's previous answers under assistant, and results returned by a called tool under tool (or function).
- NLP
Natural language processing, workloads that make sense of text already written, for example detecting sentiment, extracting key phrases and entities, or classifying it.
- OVER
Gives a T-SQL window function its window: PARTITION BY, ORDER BY and, if wanted, a ROWS or RANGE frame. Rankings and running totals can then be worked out while every row is kept.
- Key phrase extraction
Capability of Azure Language that pulls out the main ideas in a piece of text and returns them as a simple list, without confidence scores or categories.
- Entity
Something like a product or customer that an organisation stores data about. Its characteristics are its attributes, and every individual record is one instance.
- PII detection
Prebuilt Azure Language capability that finds entities such as Person, PhoneNumber, Email and Address and gives back the text with them masked. It is not a tool for moderating harmful content.
- Language detection
Capability of Azure Language that works out which language some text is in. Translation and filtering are outside its scope.
- Document Intelligence add-on capabilities
Extra Document Intelligence options switched on with the features query parameter: barcodes, formulas, keyValuePairs, languages, ocrHighResolution, queryFields and styleFont.