- Overview
- Getting Started
- Activities
- Insights Dashboards
- Document Understanding Process
- ML Packages
- Overview
- 1040 - ML Package
- 1040 Schedule C - ML Package
- 1040 Schedule D - ML Package
- 1040 Schedule E - ML Package
- 4506T - ML Package
- 990 - ML Package - Preview
- ACORD125 - ML Package
- ACORD126 - ML Package
- ACORD131 - ML Package
- ACORD140 - ML Package
- ACORD25 - ML Package
- Bank Statements - ML Package
- BillsOfLading - ML Package
- Certificate of Incorporation - ML Package
- Certificate of Origin - ML Package
- Checks - ML Package
- Children Product Certificate - ML Package
- CMS 1500 - ML Package
- EU Declaration of Conformity - ML Package
- Financial Statements - ML Package
- FM1003 - ML Package
- I9 - ML Package
- ID Cards - ML Package
- Invoices - ML Package
- Invoices Australia - ML package
- Invoices China - ML package
- Invoices India - ML package
- Invoices Japan - ML package
- Invoices Shipping - ML Package
- Packing Lists - ML Package
- Payslips - ML Package
- Passports - ML Package
- Purchase Orders - ML Package
- Receipts - ML Package
- RemittanceAdvices - ML Package
- UB04 - ML Package
- Utility Bills - ML Package
- Vehicle Titles - ML Package
- W2 - ML Package
- W9 - ML Package
- Public Endpoints
- Licensing
Build
- Upload documents and classify them automatically.
- Upload documents straight into document types.
- Manage files from the project (add, remove files and add, change tags).
- Annotate documents.
- Add or remove fields.
- Add or remove business rules.
- Have a guided experience on training classification and extraction models using the recommendations.
After successfully creating your project and uploading your documents, you can annotate them from the Build section.
You can start annotating documents from a document type section by clicking Annotate.
Uploaded documents part of a known document type are automatically pre-labeled. You can validate this from the Annotate view.
- Pre-labeling is correct and should to be validated.
- Pre-labeling is missing and should be marked as such.
- Pre-labeling is not correct and should be edited.
If all fields from a document are labeled correctly, click Confirm to validate all the fields at once.
Once a document is validated, it will be marked with a green shield in the document list.
Correct pre-labeling
Missing pre-labeling
Incorrect pre-labeling
If the pre-labeling is not correct, you can correct the field manually.You can manually label the field by creating a new field. To do this, you can select the needed information by dragging and dropping a selection box straight on the document and selecting the desired Field Name from the drop-down list.
You can change the document type settings from the Annotate view.
To do so, click on the three-dot icon ⁝ on the right side of the document type name and select Settings.
- Base model: Dataset size estimations used in the Recommended Actions depend on the base model used to train. Using the most similar base model to your Document Type will reduce the amount of annotation work required.
- Number of layouts: Dataset size estimations used in the Recommended Actions depend on the number of layouts in the dataset. More layouts generally require annotating more data.
- Number of languages: Dataset size estimation used in the Recommended Actions depend on the number of languages in the dataset. More languages generally require annotating more data.
- Document type: choose the desired document type from the drop-down list.
- Upload date: choose a date interval when the document was uploaded.
- Status: choose the status of the document
You can check your project's overall score from the top right corner. This score factors in the classifier and extractor scores for all document types. Click Project score to display the Measure section. You can check more in-depth performance measurements in that section.
You can check the score for each document type separately from the Document type section. This score factors in the overall performance of the model, as well as the size and quality of the dataset.
- Poor (0-49)
- Average (50-69)
- Good (70-89)
- Excellent (90-100)
Select Detailed model scores to go to the Measure section for detailed information.