Skip To Content

Introduction to the model

Banner image for the model

This deep learning model is used to identify or categorize entities from text. An entity may refer to a word or a sequence of words, such as the name of an organization, person, or country, or date, or time, in the text. This pretrained model detects entities from the text and classifies them into the predetermined category.

Named entity recognition (NER) can be useful when a high-level overview of a large quantity of text is required. NER can provide you crucial and important information by extracting the main entities from the text. The extracted entities are categorized into the predetermined classes and can help you make meaningful decisions and conclusions.

There are a few public datasets available for named entity recognition tasks that can extract different entities from the text. This deep learning model is trained on the OntoNotes 5 dataset and can be used to extract 18 different entities from a text in English.

License requirements

To complete this workflow, the following are the license requirements:

  • ArcGIS Pro—Advanced license
  • ArcGIS API for Python

Model details

This model has the following characteristics:

  • Input—Text on which named entity extraction will be performed.
  • Output—Classified tokens in predefined entity classes.
  • Compute—This workflow is compute intensive, and a GPU with compute capability of 6.0 or higher is recommended.
  • Entity Names Annotation—This model can extract the following 18 entities:
    • PERSON—People, including fictional
    • NORP—Nationalities or religious or political groups
    • FACILITY—Buildings, airports, highways, bridges, and so on
    • ORGANIZATION—Companies, agencies, institutions, and so on
    • GPE—Countries, cities, states
    • LOCATION—Non-GPE locations, mountain ranges, bodies of water
    • PRODUCT—Vehicles, weapons, foods, and so on (not services)
    • EVENT—Named hurricanes, battles, wars, sports events, and so on
    • WORK OF ART—Titles of books, songs, and so on
    • 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, including weight or distance
    • ORDINAL—Ordered numbers such as “first” and “second”
    • CARDINAL—Numerals that do not fall under another type
  • Accuracy metrics—This model has an accuracy of 91.6 percent.

Access and download the model

Download the Named Entity Recognition pretrained model from ArcGIS Living Atlas of the World.

  1. Browse to ArcGIS Living Atlas of the World.
  2. Sign in with your ArcGIS Online credentials.
  3. Search for Named Entity Recognition and open the item page from the search results.
  4. Click the Download button to download the model.

    You can use the downloaded .dlpk file directly in ArcGIS Pro, or upload and use it in ArcGIS Enterprise. Additionally, you can fine-tune the pretrained model if necessary.

Release notes

The following are the release notes:

DateDescription

May 2022

  • First release of Named Entity Recognition