This SageMaker model package allows you to identify and extract entities in a document, tweet, or other text.
It provides each entity’s category as well as the location in the text.
For example:
"I was in London yesterday"
Entity Type Start End
London GPE 9 15
yesterday DATE 16 25
Check out a demo
Entities supported include:
- PERSON People, including fictional.
- NORP Nationalities or religious or political groups.
- FAC Buildings, airports, highways, bridges, etc.
- ORG Companies, agencies, institutions, etc.
- GPE Countries, cities, states.
- LOC Non-GPE locations, mountain ranges, bodies of water.
- PRODUCT Objects, vehicles, foods, etc. (Not services.)
- EVENT Named hurricanes, battles, wars, sports events, etc.
- WORK_OF_ART Titles of books, songs, etc.
- LAW Named documents made into laws.
- LANGUAGE Any named language.
- DATE Absolute or relative dates or periods.
- TIME Times smaller than a day.
- PERCENT Percentage, including ”%“.
- MONEY Monetary values, including unit.
- QUANTITY Measurements, as of weight or distance.
- ORDINAL “first”, “second”, etc.
- CARDINAL Numerals that do not fall under another type.
The model currently only supports English.
How to use this SageMaker model package
After subscribing to the product, you can make predictions
using the AWS SageMaker API, or host a REST API for your application.
You can also use SageMaker to do batch processing (batch transform) of your documents and
process multiple text segments at once.
See the Amazon SageMaker documentation
for more information.
FAQ
What is a SageMaker model package?
- You can use SageMaker model packages to build a deployable model in SageMaker.
- You can use the deployable model for real-time inference by hosting it on SageMaker hosting services.
- You can also get inferences for an entire dataset by running batch transform jobs.
See also Deploy a Model in Amazon SageMaker
How much does it cost?
The model is currently priced per hour. See the product page on AWS Marketplace for more information.
Contact us if you require a customized pricing model.