NLP pipelines combine a sequence that may contain:
- Converters to transform source formats
- Custom-made or off-the-shelf models, annotators and processors to manipulate text or annotations,
- Formatters 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 and combine components:
- Document conversion: select a converter
- Processing pipeline: select a sequence of models, gazetteers, annotators, processors…
- When adding a component to a pipeline, you can select either:
- Project annotators that are part of existing projects or
- External annotators independently of any existing project.
- You can add conditions under which a particular annotator is launched
- Output format: select a formatter
- Save the pipeline with the tick button at the top right of the window.
- Then go to the Annotation Tests view to test the pipeline with the text of a new document. Pipelines are all listed in the drop down menu alongside models, gazetteers, suggestions models of your current project.