Stay organized with collectionsSave and categorize content based on your preferences.
This page documents production updates to Natural Language. We recommend
that Natural Language developers periodically check this list for any
new announcements. Major changes will also be announced via thecloud-nl-discussmailing list.
You can see the latest product updates for all of Google Cloud on theGoogle Cloudpage, browse and filter all release notes in theGoogle Cloud console,
or programmatically access release notes inBigQuery.
To get the latest product updates delivered to you, add the URL of this page to yourfeed
reader, or add thefeed URLdirectly.
August 28, 2023
The Natural Language API v2 is now available inPublic Preview. This new version of the API supports Sentiment Analysis, Entity Analysis, Text Moderation, and Content Classification. This version has major updates for Sentiment Analysis and Entity Analysis, which include performance upgrades and general improvements. All API calls now returnlanguage_code.
Sentiment analysis uses a new PaLM-based model for improved quality. Thelanguagefield is now calledlanguage_code.
Entity analysis uses a new PaLM-based model for improved quality. Please note the following updates:
languagefield is now called "language_code"
Nosaliencefield.
Nowikipedia_urlas metadata.
Parsing improvements for the following entity types: PHONE_NUMBER, ADDRESS, DATE, NUMBER, PRICE
Newprobabilityscore field is returned for all entities where NUMBER, PHONE_NUMBER, ADDRESS, PRICE, DATE will always be 1.0.
January 31, 2023
Natural Language Content Classification v2 model is nowGenerally Available. This model supports an expanded taxonomy with 1091 content categories and 11 languages. The model is distilled from a Large Language Model with improved performance over the v1 offering.
October 18, 2022
Natural Language Content Classification v2 model is now in PublicPreview. This model supports an expanded taxonomy with 1091 content categories and 11 languages. The model is distilled from a Large Language Model with improved performance over the v1 offering.
March 20, 2020
The Natural Language API now supportsadditional languagesfor sentiment analysis.
February 20, 2020
The Natural Language API now offers twomultiregion endpoints(us-language.googleapis.comandeu-language.googleapis.com).
Using a multiregion endpoint enables you to configure the Natural Language API to
store and perform machine learning on your data in the United States or European Union.
May 03, 2019
The Natural Language API now supportsSpanishfor entity sentiment analysis.
April 04, 2019
The Natural Language API now supportsRussianfor entity analysis and syntactic analysis, and Japanese for entity sentiment analysis.
TheanalyzeEntitiesmethod identifies and returnsadditional entity types: phone numbers, addresses, dates, prices, and numbers.
November 16, 2017
Cloud Natural Language API version 1.2 GA release.
The Natural Language API has released the newclassifyTextmethod that analyzes text content and returns a content category for the content. For more information, seeContent Classification.
September 19, 2017
The Natural Language APIv1now supports entity sentiment analysis with theanalyzeEntitySentimentmethod. Entity sentiment analysis is currently only available for the English language. For more information, seeEntity Sentiment Analysis.
The Natural Language APIv1beta2has added beta support for a newclassifyTextmethod that analyzes text content and returns a content category for the content. For more information, seeContent Classification.
August 04, 2017
The following languages are now fully supported for entity, sentiment, and syntax analysis:
* Chinese (Simplified and Traditional)
* French
* German
* Italian
* Korean
* Portuguese
Sentiment analysis has been updated. You might see minor differences in score and magnitude from the same request made to previous releases.
Entity analysis has been updated. You might see minor differences in metadata (Wikipedia URLs, knowledge graph MIDs) of entities identified in a block of text from the same request made to the previous releases.
May 02, 2017
Cloud Natural Language APIv1beta2release. Added beta support for entity, sentiment, and syntax analysis for the following languages:
* Chinese (Simplified and Traditional)
* French
* German
* Italian
* Korean
* Portuguese
Added beta support for entity sentiment analysis (analyzeEntitySentiment). Entity sentiment analysis is currently only available for the English language. For more information, seeEntity Sentiment Analysis.
Thev1beta2release includes updated document sentiment analysis. You might see differing results from the same request made to the Natural Language APIv1andv1beta2releases.
Thev1beta2release includes updated entity analysis. You might see minor differences in metadata (Wikipedia URLs, knowledge graph MIDs) from the same request made to the Natural Language APIv1andv1beta2releases.
The Natural Language APIv1beta1release has been deprecated.
November 15, 2016
Promoted the Cloud Natural Language API from Beta (v1beta1) to General Availability (v1).
Updates for v1 from the previous v1beta1 API endpoint include the features listed below.
The sentiment analysis feature has these enhancements:
* Support for Japanese (ja) and Spanish (es)
* Availability ofsentence level sentiment* Support forEncodingTypewithin a Sentiment Analysis request to calculate offsets for sentence-level sentiment
*Addition of ascorefield within theSentimenttype to replace the previouspolarityfield
The entity analysis feature has these enhancements:
* Added Google Knowledge Graph MID values, if available, to themetadatafield for eachEntityreturned
* ReturnsEntity Mention Typesfor both proper nouns and common nouns (known as "nominals")
Syntactic analysis has these enhancements:
* Added a newanalyzeSyntaxmethod
* Added morphology support to returnedtokens
Removed thepolarityfield within theSentimenttype in favor of the newscorefield.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Natural Language release notes\n\nThis page documents production updates to Natural Language. We recommend\nthat Natural Language developers periodically check this list for any\nnew announcements. Major changes will also be announced via the\n[cloud-nl-discuss](https://groups.google.com/forum/#!forum/cloud-nl-discuss)\nmailing list.\n\nYou can see the latest product updates for all of Google Cloud on the\n[Google Cloud](/release-notes) page, browse and filter all release notes in the\n[Google Cloud console](https://console.cloud.google.com/release-notes),\nor programmatically access release notes in\n[BigQuery](https://console.cloud.google.com/bigquery?p=bigquery-public-data&d=google_cloud_release_notes&t=release_notes&page=table).\n\nTo get the latest product updates delivered to you, add the URL of this page to your\n[feed\nreader](https://wikipedia.org/wiki/Comparison_of_feed_aggregators), or add the\n[feed URL](https://cloud.google.com/feeds/language-release-notes.xml) directly.\n\nAugust 28, 2023\n---------------\n\nThe Natural Language API v2 is now available in [Public Preview](https://cloud.google.com/products#product-launch-stages). This new version of the API supports Sentiment Analysis, Entity Analysis, Text Moderation, and Content Classification. This version has major updates for Sentiment Analysis and Entity Analysis, which include performance upgrades and general improvements. All API calls now return `language_code` . \nSentiment analysis uses a new PaLM-based model for improved quality. The `language` field is now called `language_code`. \nEntity analysis uses a new PaLM-based model for improved quality. Please note the following updates:\n\n- **language** field is now called \"language_code\"\n- No **salience** field.\n- No **wikipedia_url** as metadata.\n- Parsing improvements for the following entity types: PHONE_NUMBER, ADDRESS, DATE, NUMBER, PRICE\n- New **probability** score field is returned for all entities where NUMBER, PHONE_NUMBER, ADDRESS, PRICE, DATE will always be 1.0.\n\nJanuary 31, 2023\n----------------\n\nNatural Language Content Classification v2 model is now [Generally Available](https://cloud.google.com/products#product-launch-stages). This model supports an expanded taxonomy with 1091 content categories and 11 languages. The model is distilled from a Large Language Model with improved performance over the v1 offering.\n\nOctober 18, 2022\n----------------\n\nNatural Language Content Classification v2 model is now in Public [Preview](https://cloud.google.com/products#product-launch-stages). This model supports an expanded taxonomy with 1091 content categories and 11 languages. The model is distilled from a Large Language Model with improved performance over the v1 offering.\n\nMarch 20, 2020\n--------------\n\nThe Natural Language API now supports [additional languages](https://cloud.google.com/natural-language/docs/languages#sentiment_analysis) for sentiment analysis.\n\nFebruary 20, 2020\n-----------------\n\nThe Natural Language API now offers two [multiregion endpoints](https://cloud.google.com/natural-language/docs/locations) (`us-language.googleapis.com` and `eu-language.googleapis.com`).\nUsing a multiregion endpoint enables you to configure the Natural Language API to\nstore and perform machine learning on your data in the United States or European Union.\n\nMay 03, 2019\n------------\n\nThe Natural Language API now supports [Spanish](https://cloud.google.com/natural-language/docs/languages) for entity sentiment analysis.\n\nApril 04, 2019\n--------------\n\nThe Natural Language API now supports [Russian](https://cloud.google.com/natural-language/docs/languages) for entity analysis and syntactic analysis, and Japanese for entity sentiment analysis. \nThe `analyzeEntities` method identifies and returns [additional entity types](https://cloud.google.com/natural-language/docs/reference/rest/v1/Entity#Type): phone numbers, addresses, dates, prices, and numbers.\n\nNovember 16, 2017\n-----------------\n\nCloud Natural Language API version 1.2 GA release. \nThe Natural Language API has released the new `classifyText` method that analyzes text content and returns a content category for the content. For more information, see [Content Classification](https://cloud.google.com/natural-language/docs/basics#content-classification).\n\nSeptember 19, 2017\n------------------\n\nThe Natural Language API `v1` now supports entity sentiment analysis with the `analyzeEntitySentiment` method. Entity sentiment analysis is currently only available for the English language. For more information, see [Entity Sentiment Analysis](https://cloud.google.com/natural-language/docs/basics#entity-sentiment-analysis). \nThe Natural Language API `v1beta2` has added beta support for a new `classifyText` method that analyzes text content and returns a content category for the content. For more information, see [Content Classification](https://cloud.google.com/natural-language/docs/basics#content-classification).\n\nAugust 04, 2017\n---------------\n\nThe following languages are now fully supported for entity, sentiment, and syntax analysis:\n\\* Chinese (Simplified and Traditional)\n\\* French\n\\* German\n\\* Italian\n\\* Korean\n\\* Portuguese \nSentiment analysis has been updated. You might see minor differences in score and magnitude from the same request made to previous releases. \nEntity analysis has been updated. You might see minor differences in metadata (Wikipedia URLs, knowledge graph MIDs) of entities identified in a block of text from the same request made to the previous releases.\n\nMay 02, 2017\n------------\n\nCloud Natural Language API `v1beta2` release. Added beta support for entity, sentiment, and syntax analysis for the following languages:\n\\* Chinese (Simplified and Traditional)\n\\* French\n\\* German\n\\* Italian\n\\* Korean\n\\* Portuguese \nAdded beta support for entity sentiment analysis (`analyzeEntitySentiment`). Entity sentiment analysis is currently only available for the English language. For more information, see [Entity Sentiment Analysis](https://cloud.google.com/natural-language/docs/basics#entity-sentiment-analysis). \nThe `v1beta2` release includes updated document sentiment analysis. You might see differing results from the same request made to the Natural Language API `v1` and `v1beta2` releases. \nThe `v1beta2` release includes updated entity analysis. You might see minor differences in metadata (Wikipedia URLs, knowledge graph MIDs) from the same request made to the Natural Language API `v1` and `v1beta2` releases. \nThe Natural Language API `v1beta1` release has been deprecated.\n\nNovember 15, 2016\n-----------------\n\nPromoted the Cloud Natural Language API from Beta (v1beta1) to General Availability (v1).\nUpdates for v1 from the previous v1beta1 API endpoint include the features listed below. \nThe sentiment analysis feature has these enhancements:\n\\* Support for Japanese (`ja`) and Spanish (`es`)\n\\* Availability of [sentence level sentiment](https://cloud.google.com/natural-language/docs/reference/rest/v1/documents/analyzeSentiment#response-body)\n\\* Support for [EncodingType](https://cloud.google.com/natural-language/docs/reference/rest/v1/EncodingType) within a Sentiment Analysis request to calculate offsets for sentence-level sentiment\n\\*Addition of a `score` field within the [`Sentiment`](https://cloud.google.com/natural-language/docs/reference/rest/v1/Sentiment) type to replace the previous `polarity` field \nThe entity analysis feature has these enhancements:\n\\* Added Google Knowledge Graph MID values, if available, to the [`metadata` field for each `Entity`](https://cloud.google.com/natural-language/docs/reference/rest/v1/Entity) returned\n\\* Returns [Entity Mention Types](https://cloud.google.com/natural-language/docs/reference/rest/v1/Entity#type_1) for both proper nouns and common nouns (known as \"nominals\") \nSyntactic analysis has these enhancements:\n\\* Added a new [`analyzeSyntax`](https://cloud.google.com/natural-language/docs/reference/rest/v1/documents/analyzeSyntax) method\n\\* Added morphology support to returned [tokens](https://cloud.google.com/natural-language/docs/reference/rest/v1/Token) \nRemoved the `polarity` field within the [`Sentiment`](https://cloud.google.com/natural-language/docs/reference/rest/v1/Sentiment) type in favor of the new `score` field."]]
