NER labeling with Flair

Flair NER example

This example demonstrates how to use Flair NER model with Label Studio.

Quickstart

  1. Build and start the Machine Learning backend on http://localhost:9090
docker-compose up
  1. Validate that the backend is running
$ curl http://localhost:9090/health
{"status":"UP"}
  1. Create a project in Label Studio. Then from the Model page in the project settings, connect the model. The default URL is http://localhost:9090.

Labeling Configuration

<View>
  <Labels name="label" toName="text">
    <Label value="PER" background="red"/>
    <Label value="ORG" background="darkorange"/>
    <Label value="LOC" background="orange"/>
    <Label value="MISC" background="green"/>
  </Labels>

  <Text name="text" value="$text"/>
</View>

Parameters

  • FLAIR_MODEL_NAME: The name of the Flair model to use. Default is ner. See all options here