Stay organized with collections
Save and categorize content based on your preferences.
Most apps offer users very little interaction with text beyond the basic
cut/copy/paste operations. Entity extraction improves the user experience inside
your app by understanding text and allowing you to add helpful shortcuts based
on context.
The entity extraction API allows you to recognize specific entities within
static text and while you're typing. Once an entity is identified, you can
easily enable different actions for the user based on the entity type. Supported
entities included are:
Entity
Example
Address
350 third street, Cambridge MA
Date-Time
2019/09/29, let's meet tomorrow at 6pm
Email address
entity-extraction@google.com
Flight Number (IATA flight codes only)
LX37
IBAN
CH52 0483 0000 0000 0000 9
ISBN (version 13 only)
978-1101904190
Money/Currency (Arabic numerals only)
$12, 25 USD
Payment / Credit Cards
4111 1111 1111 1111
Phone Number
(555) 225-3556
12345
Tracking Number (standardized international formats)
This API focuses on precision over recognition. Some instances of a particular
entity might not be detected in favor of ensuring accuracy.
Most entities can be detected across languages and locales. The ability to
detect addresses and phone numbers depends on the selected language. Entity
extraction supports the following languages:
Arabic
Portuguese
English (US, UK)
Dutch
French
German
Italian
Japanese
Korean
Polish
Russian
Chinese (Simplified, Traditional)
Spanish
Thai
Turkish
Examples
Input text
Detected entities
Meet me at 1600 Amphitheatre Parkway, Mountain View, CA, 94043
Let’s organize a meeting to discuss.
[null,null,["Last updated 2024-07-10 UTC."],[[["\u003cp\u003eThe Entity Extraction API identifies specific entities like addresses, dates, emails, and more within text, enabling context-aware actions in your app.\u003c/p\u003e\n"],["\u003cp\u003eThis API prioritizes accuracy, potentially missing some entity instances to ensure precision in its identification.\u003c/p\u003e\n"],["\u003cp\u003eEntity extraction supports a wide range of languages, including English, Spanish, Chinese, Japanese, and others, although address and phone number detection depends on the specific language.\u003c/p\u003e\n"],["\u003cp\u003eWhile in beta, this API is not subject to an SLA or deprecation policy, and backward-compatibility breaking changes may occur.\u003c/p\u003e\n"]]],[],null,["# Entity extraction\n\n| This API is offered in beta, and is not subject to any SLA or deprecation policy. Changes may be made to this API that break backward compatibility.\n\nMost apps offer users very little interaction with text beyond the basic\ncut/copy/paste operations. Entity extraction improves the user experience inside\nyour app by understanding text and allowing you to add helpful shortcuts based\non context.\n\n[iOS](/ml-kit/language/entity-extraction/ios)\n[Android](/ml-kit/language/entity-extraction/android)\n\nThe entity extraction API allows you to recognize specific entities within\nstatic text and while you're typing. Once an entity is identified, you can\neasily enable different actions for the user based on the entity type. Supported\nentities included are:\n\n| Entity | Example |\n|------------------------------------------------------|-------------------------------------------------------|\n| Address | 350 third street, Cambridge MA |\n| Date-Time | 2019/09/29, let's meet tomorrow at 6pm |\n| Email address | entity-extraction@google.com |\n| Flight Number (IATA flight codes only) | LX37 |\n| IBAN | CH52 0483 0000 0000 0000 9 |\n| ISBN (version 13 only) | 978-1101904190 |\n| Money/Currency (Arabic numerals only) | $12, 25 USD |\n| Payment / Credit Cards | 4111 1111 1111 1111 |\n| Phone Number | (555) 225-3556 12345 |\n| Tracking Number (standardized international formats) | 1Z204E380338943508 |\n| URL | www.google.com https://en.wikipedia.org/wiki/Platypus |\n\nThis API focuses on precision over recognition. Some instances of a particular\nentity might not be detected in favor of ensuring accuracy.\n\nMost entities can be detected across languages and locales. The ability to\ndetect addresses and phone numbers depends on the selected language. Entity\nextraction supports the following languages:\n\n- Arabic\n- Portuguese\n- English (US, UK)\n- Dutch\n- French\n- German\n- Italian\n- Japanese\n- Korean\n- Polish\n- Russian\n- Chinese (Simplified, Traditional)\n- Spanish\n- Thai\n- Turkish\n\nExamples\n--------\n\n| Input text | Detected entities |\n|-------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------|\n| Meet me at 1600 Amphitheatre Parkway, Mountain View, CA, 94043 Let's organize a meeting to discuss. | Entity 1 type: Address Entity 1 text: \"1600 Ampitheatre Parkway, Mountain View, CA 94043\" |\n| You can contact the test team tomorrow at info@google.com to determine the best timeline. | Entity 1 type: Date-Time Entity 1 text: = \"June 24th, 2020\" Entity 2 type: Email address Entity 2 text: info@google.com |\n| Your order has shipped from Google. To follow the progress of your delivery please use this tracking number: 9612804152073070474837 | Entity type: Tracking number Entity text: \"9612804152073070474837\" |\n| Call the restaurant at 555-555-1234 to pay for dinner. My card number is 4111-1111-1111-1111. | Entity 1 type: Phone number Entity 1 text: \"555-555-1234\" Entity 2 type: Payment card Entity 2 text: \"4111 1111 1111 1111\" |"]]
