An NLP pipeline combine a sequence that may contain:
- a converter to transform source formats
- custom-made or off-the-shelf models, annotators and processors to manipulate text or annotations,
- a formatter to provide the desired output format.
To create a pipeline:
- Go to the Pipelines view
- Create a new pipeline
- Give a name to the pipeline.
- Select a possible converter if necessary (you don’t need any converter if you deal with raw text)
- Add a first item in your pipeline clicking on the +
- When adding a component to a pipeline, you can select either:
- Model or Pipeline that are part of existing projects or
- Off-the-shelf annotator independently of any existing project
- Select a project you have access to and then select a model
- Add another model as you wish
- Add an off-the-shelf component as below.
- You will have acces to a large library of off-the-shelf models & technical components.
- Select for instance the Consolidation component as below. This component aims at dedupplicating annotations between two similar models that might extract the same type of information.
- You can configure the component with the parameters in the right panel.
- You can add conditions under which a particular model, annotator or component is launched
- Finally, you can select a possible formatter to have a different output format that the Kairntech JSON format.
- Save the pipeline with the tick button at the top right of the window.
- Then, as a single model, you can test your pipeline