- Overview
- Getting started
- Building models
- Consuming models
- ML packages
- 1040 - ML package
- 1040 Schedule C - ML package
- 1040 Schedule D - ML package
- 1040 Schedule E - ML package
- 1040x - ML package
- 3949a - ML package
- 4506T - ML package
- 709 - ML package
- 941x - ML package
- 9465 - ML package
- ACORD125 - ML package
- ACORD126 - ML package
- ACORD131 - ML package
- ACORD140 - ML package
- ACORD25 - ML package
- Bank Statements - ML package
- Bills Of Lading - 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 Hebrew - 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
- Receipts Japan - ML package
- Remittance Advices - ML package
- UB04 - ML package
- Utility Bills - ML package
- Vehicle Titles - ML package
- W2 - ML package
- W9 - ML package
- Public endpoints
- Supported languages
- Insights dashboards
- Data and security
- Licensing
- How to
Document Understanding Modern Projects User Guide
Annotation best practices
Before you begin the annotation process, it's important to create a comprehensive list of all the necessary fields for the particular type of document. Define each field clearly to prevent any confusion. Depending on your preference, you can use a sample document and annotate it as an example, or you can create a detailed table that explains each field.
- Column fields
- Regular fields
If you notice a field appearing multiple times in the same document and with the same value, make sure to annotate each instance of this field. For instance, if the invoice number appears both at the top and bottom of the document, you should annotate both instances.
In cases where values differ, you should only annotate the correct value. This can also apply to instances where the value varies across different documents from the same vendor or variation. In such situations, always prioritizing vendor consistency is key, even if this means ignoring values that occasionally differ.
An important principle is to maintain consistency when annotating across similar layouts. This ensures clean and uniform data.
Additionally, make sure all annotated data is complete. Double-check to avoid missing words in addresses or other critical information.
Date: 28-11-2022 as the date, make sure to remove
Date:. This keeps your information succinct and precise.
If you are working with multiple tables, remember that each column in every table needs its own column field. This process is important to accurately and effectively capturing data.
/ hotkey. This will tie the
fields together and enable more efficient processing of the table.
CTRL+Left Click, and then select / to achieve
this group. This enables the system to read rows seamlessly, even when they span
multiple pages.
