What's new in Azure AI Language?
Azure AI Language is updated on an ongoing basis. To stay up-to-date with recent developments, this article provides you with information about new releases and features.
February 2024
- Expanded language detection support for additional scripts according to the ISO 15924 standard is now available starting in API version
2023-11-15-preview.
January 2024
- Native document support is now available in
2023-11-15-previewpublic preview.
December 2023
- Text Analytics for health new model 2023-12-01 is now available.
- New Relation Type:
BodySiteOfExamination - Quality enhancements to support radiology documents
- Significant latency improvements
- Various bug fixes: Improvements across NER, Entity Linking, Relations and Assertion Detection
November 2023
- Named Entity Recognition Container is now Generally Available (GA).
July 2023
- Custom sentiment analysis is now available in preview.
May 2023
- Custom Named Entity Recognition (NER) Docker containers are now available for on-premises deployment.
April 2023
- Custom Text analytics for health is available in public preview, which enables you to build custom AI models to extract healthcare specific entities from unstructured text
- You can now use Azure OpenAI to automatically label or generate data during authoring. Learn more with the following links:
- Autolabel your documents in Custom text classification or Custom named entity recognition.
- Generate suggested utterances in Conversational language understanding.
- The latest model version (
2022-10-01) for Language Detection now supports 6 more International languages and 12 Romanized Indic languages.
March 2023
New model version ('2023-01-01-preview') for Personally Identifiable Information (PII) detection with quality updates and new language support
New versions of the text analysis client library are available in preview:
February 2023
- Conversational language understanding and orchestration workflow now available in the following regions in the sovereign cloud for China:
- China East 2 (Authoring and Prediction)
- China North 2 (Prediction)
- New model evaluation updates for Conversational language understanding and Orchestration workflow.
- New model version ('2023-01-01-preview') for Text Analytics for health featuring new entity categories for social determinants of health.
- New model version ('2023-02-01-preview') for named entity recognition features improved accuracy and more language support with up to 79 languages.
December 2022
- New version (v5.2.0-beta.1) of the text analysis client library is available in preview for C#/.NET:
- New model version (
2022-10-01) released for Language Detection. The new model version comes with improvements in language detection quality on short texts.
November 2022
Expanded language support for:
Conversational PII now supports up to 40,000 characters as document size.
New versions of the text analysis client library are available in preview:
October 2022
- The summarization feature now has the following capabilities:
- Document summarization:
- Abstractive summarization, which generates a summary of a document that can't use the same words as presented in the document, but captures the main idea.
- Conversation summarization
- Chapter title summarization, which returns suggested chapter titles of input conversations.
- Narrative summarization, which returns call notes, meeting notes or chat summaries of input conversations.
- Document summarization:
- Expanded language support for:
- Multi-region deployment and project asset versioning for:
- Regular expressions in conversational language understanding and required components, offering an added ability to influence entity predictions.
- Entity resolution in named entity recognition
- New region support for:
- Document type as an input supported for Text Analytics for health FHIR requests
September 2022
- Conversational language understanding is available in the following regions:
- Central India
- Switzerland North
- West US 2
- Text Analytics for Health now supports more languages in preview: Spanish, French, German Italian, Portuguese and Hebrew. These languages are available when using a docker container to deploy the API service.
- The Azure.AI.TextAnalytics client library v5.2.0 are generally available and ready for use in production applications. For more information on Language service client libraries, see the Developer overview.
August 2022
- Role-based access control for the Language service.
July 2022
New AI models for sentiment analysis and key phrase extraction based on z-code models, providing:
- Performance and quality improvements for the following 11 languages supported by sentiment analysis:
ar,da,el,fi,hi,nl,no,pl,ru,sv,tr - Performance and quality improvements for the following 20 languages supported by key phrase extraction:
af,bg,ca,hr,da,nl,et,fi,el,hu,id,lv,no,pl,ro,ru,sk,sl,sv,tr
- Performance and quality improvements for the following 11 languages supported by sentiment analysis:
Conversational PII is now available in all Azure regions supported by the Language service.
A new version of the Language API (
2022-07-01-preview) is available. It provides:- Automatic language detection for asynchronous tasks.
- Text Analytics for health confidence scores are now returned in relations.
To use this version in your REST API calls, use the following URL:
<your-language-resource-endpoint>/language/:analyze-text?api-version=2022-07-01-preview
June 2022
- v1.0 client libraries for conversational language understanding and orchestration workflow are Generally Available for the following languages:
- v1.1.0b1 client library for conversation summarization is available as a preview for:
- There's a new endpoint URL and request format for making REST API calls to prebuilt Language service features. See the following quickstart guides and reference documentation for information on structuring your API calls. All text analytics
3.2-preview.2API users can begin migrating their workloads to this new endpoint.
May 2022
PII detection for conversations.
Rebranded Text Summarization to Document summarization.
Conversation summarization is now available in public preview.
The following features are now Generally Available (GA):
- Custom text classification
- Custom Named Entity Recognition (NER)
- Conversational language understanding
- Orchestration workflow
The following updates for custom text classification, custom Named Entity Recognition (NER), conversational language understanding, and orchestration workflow:
- Data splitting controls.
- Ability to cancel training jobs.
- Custom deployments can be named. You can have up to 10 deployments.
- Ability to swap deployments.
- Auto labeling (preview) for custom named entity recognition
- Enterprise readiness support
- Training modes for conversational language understanding
- Updated service limits
- Ability to use free (F0) tier for Language resources
- Expanded regional availability
- Updated model life cycle to add training configuration versions
April 2022
- Fast Healthcare Interoperability Resources (FHIR) support is available in the Language REST API preview for Text Analytics for health.
March 2022
- Expanded language support for:
February 2022
Model improvements for latest model-version for text summarization
Model
2021-10-01is Generally Available (GA) for Sentiment Analysis and Opinion Mining, featuring enhanced modeling for emojis and better accuracy across all supported languages.Question Answering: Active learning v2 incorporates a better clustering logic providing improved accuracy of suggestions. It considers user actions when suggestions are accepted or rejected to avoid duplicate suggestions, and improve query suggestions.
December 2021
- The version 3.1-preview.x REST endpoints and 5.1.0-beta.x client library are retired. Upgrade to the General Available version of the API(v3.1). If you're using the client libraries, use package version 5.1.0 or higher. See the migration guide for details.
November 2021
Based on ongoing customer feedback, we increased the character limit per document for Text Analytics for health from 5,120 to 30,720.
Azure AI Language release, with support for:
- Question Answering (now Generally Available)
- Sentiment Analysis and opinion mining
- Key Phrase Extraction
- Named Entity Recognition (NER), Personally Identifying Information (PII)
- Language Detection
- Text Analytics for health
- Text summarization preview
- Custom Named Entity Recognition (Custom NER) preview
- Custom Text Classification preview
- Conversational Language Understanding preview
Preview model version
2021-10-01-previewfor Sentiment Analysis and Opinion mining, which provides:- Improved prediction quality.
- Added language support for the opinion mining feature.
- For more information, see the project z-code site.
- To use this model version, you must specify it in your API calls, using the model version parameter.
SDK support for sending requests to custom models:
- Custom Named Entity Recognition
- Custom text classification
- Custom language understanding
Next steps
- See the previous updates article for service updates not listed here.
Feedback
Coming soon: Throughout 2024 we will be phasing out GitHub Issues as the feedback mechanism for content and replacing it with a new feedback system. For more information see: https://aka.ms/ContentUserFeedback.
Submit and view feedback for