[43.1] Document Classification Task

Classification models in Hyperscience

Classification models are a crucial part of document processing as they help the system determine which layout should be used to process each page you upload. In Hyperscience, we have two types of document classification:

Structured Document Classification - Automatically classifies documents that follow a consistent layout pattern (e.g., tax forms, standardized applications) by assigning them to the correct layout in Hyperscience. Once classified, the documents can proceed to the next step - Field Identification Task, Transcription Task, or Flexible Extraction, depending on your business logic. Learn more in Structured Document Classification.
Semi-structured Document Classification - Automatically classifies documents that don’t follow a consistent layout pattern (e.g., invoices, bank statements, etc.). To learn more, see Semi-structured Document Classification and TDM for Classification Models.

In this article, you’ll learn how to work with Document Classification Task. Learn more about Identification in TDM for Identification Models. To learn about Transcription and Flexible Extraction, see our Transcription and Flexible Extraction articles.

Document Classification task

Document Classification is a Supervision task used to group pages into documents and assign the correct layout. These tasks are created when automatic classification isn’t possible (e.g., when no model is available or the model’s confidence is low).

Expand the section below to learn how to navigate the interface and complete a Document Classification task.

Document Classification Interface

To open a Document Classification task, go to the Tasks section and click Perform Tasks under the Supervision task type table.

Document Classification allows you to:

Add uncategorized pages to grouped documents.
Reorder pages in grouped documents.
Remove pages from grouped documents.
Classify (apply layouts to) manually grouped documents.
Reclassify (apply different layouts to) machine-misclassified documents.

Left Panel - Uncategorized

The left panel displays all uncategorized pages - pages that haven’t yet been grouped into a document.

Order of Uncategorized pages
Pages in this panel appear in the order they were submitted to the system, with a thumbnail preview for quick scanning.

Select pages using your mouse or keyboard shortcuts.
- For a full shortcut list, click thebutton.
You can also select all uncategorized pages by clicking the Select All button.
Click the Create New Doc (OPTION+N) button to group the selected pages into a new document.
- To submit the Document Classification task, all pages from the left panel must be categorized.

Starting in 43.1, grouping uncategorized pages includes layout or filename
In the Uncategorized Pages Panel, you can toggle between three views using the tabs at the top:
All —Displays a flat list of all uncategorized pages (default view).
Layout — Groups pages based on the machine's best-guess layout prediction. This view includes an inline warning reminding you to review machine predictions, as well as confidence scores for each prediction.
Filename — Groups pages based on the original filename of the submission.
These grouping options can help you review, compare, and process related pages more efficiently during manual classification.

Middle Panel - Grouped Documents

The middle panel shows all documents you’ve grouped.

In this panel, you can:

Select a layout from the drop-down.
- If a page doesn’t match any of the available layouts, you can use one of the categories below:
  - Additional Form Page (No Layout Found) - Sends the page to the No Layout Found workflow for review. These pages can be reviewed later and may help define a new layout. To learn more, see Document Drift Management (Layout Triage) and Creating Additional Layouts.
  - Blank Page - Marks the page as blank. It’s excluded from processing.
  - Excluded (formerly “Other”) - pages used as counter-examples for Semi-structured classification. To learn more, see TDM for Classification Models

Searching for a specific layout
You can search for a specific layout using the Layout Group drop-down list.

Select a layout variation from the drop-down list.

Searching for layout variations
You can search for and select a layout variation directly from the Layout Variation drop-down list. Selecting a layout variation automatically assigns the corresponding layout group.

Create a new document using the selected pages.
Reclassify documents that were incorrectly grouped.

Page Numbers
All pages in the left and middle panels show their submission page number based on the order in which they were uploaded.
Grouped documents are sorted by the submission number of their first page.
When you create a new document manually, the pages are automatically ordered by submission number.

Add, remove, and reorder pages within a document.
- Add a page from one document to another, using the Add to Doc button. Note that this will be treated as a manual match, and the content on the page will require manual extraction.
  - To move a page between documents, make sure both documents use the same layout variation.
- To move a page to the last position in the document, click the Append page button. Note that if you choose to append it, the machine’s confidence will drop, and it will be sent for manual extraction.
- Remove a page by clicking the button or pressing DEL on your keyboard.
- Reorder pages using the shortcuts or
  - Select the page you want to reorder and drag it to the desired position.
When a page is appended or manually matched, it is highlighted with an orange border. Hovering over the page displays a tooltip indicating that the page was manually classified. This border is shown in both Manual Classification and Flexible Extraction tasks.

Right Panel - Document Preview

The right panel shows a zoomable full-page view of the selected page.

Rotate the page by clicking the button or using your keyboard.

Machine-classified grouped documents rotation
Pages in machine-classified grouped documents can not be modified in place. You need to remove the page from the document and once it falls under Uncategorized, you can rotate it.
You can rotate all selected Uncategorized pages 90° clockwise.
During Machine Classification, the page image may be adjusted in order to obtain a match. Deselect Machine Adjusted Image by clicking the button on the page’s preview in the left or right panel to reset the image to its submission state.

To complete the task, click Submit (CMD+Enter).

Reprocessing Misclassified documents

If a document is marked as Layout Incorrect during Flexible Extraction, Identification, or Transcription Supervision, you can reprocess it and send it back to Document Classification for rework.

Instead of being marked as Complete, the submission remains in progress until all documents are properly classified.

Using Reprocessing

You can trigger reprocessing from any Identification or Transcription Supervision or Flexible Extraction task. To learn more, see Supervision and QA Introduction.

Go to Submissions.
Find the mismatched submission by its ID.
Click on the Perform Tasks link in the Tasks column for the submission.
In the right sidebar of the task, expand the document information and click Mark Layout Variation Incorrect.
- Doing so removes the layout from all pages of the current document and creates a Document Classification task.

Click Continue on the warning message.
- The document status changes to Reprocessing and is sent back to Document Classification.
  - On the Document Classification task, you’ll see the following message:

If multiple documents are affected, all must be completed before the submission status updates.

Reclassify your documents by following the guidance in Document Classification Interface section.

After you’ve classified your Structured documents, the next step is to extract the data you need. Learn how to work with Flexible Extraction by reading our Flexible Extraction article.

Documentation Index