Like to seek your opinion on how I should approach the tasks in terms of workflow.
- I annotate the dataset first by labelling the entities and then build a NER model
- Use the NER model generated and run it on the same dataset as in step #1 and together with the entities inferred by the model, label the relation between entities and build another relation model.
- I annotate the entities and relation on the dataset.
- Build a NER model using the annotated file.
- Build a entity relation model using the same annotated file (same file as in step 2).