Get our latest book on "Top 10 artificial intelligence myths."
Download

Last updated

September 30, 2021

Table of contents

How to extract data from tables

Extracting data from tables is a beta feature. We’d love for you to join our table extraction beta program, take it through the paces, and give us any feedback. Contact feedback@impira.com to access this new feature. 

Step 1: Start by labeling Row 1

Once you’ve uploaded your file and placed it into a collection, open a file to enter File view.



  1. Go to Add field in the top right corner and select Table.
  2. Give your table a name.


  1. Find and highlight the table’s first value (e.g., 500). See the graphic below for examples of first values.


Two examples of the first value (“500”) for the first field name (“QTY”).

  1. Enter the field name (e.g., QTY) and select Save and add another table field to continue. (Note: Impira will auto-detect the field type (text, number, or date), but feel free to take a look and change the type if necessary.)
  2. Repeat steps 3 and 4 until each table field is added to your row (e.g., QTY, Unit, Description, Price, etc).


Behind the magic: What’s happening?

As you label the values for Row 1, Impira actively learns and uses your input to piece together what you’re trying to accomplish. Impira is already going through the rest of your table rows (for this file and for others in your collection) to extract the same data fields.

You’ll see Impira’s predictions show up in a queue in File view in just a few moments. If you don’t see any show up, you may have to label a few more fields in a new row. 

Impira never stops learning. As you review predictions, Impira will automatically apply your input and reprocess previous predictions to make them better. With just a handful of points and clicks, you’re making life easier by creating a more fine-tuned machine learning model that’ll perform better for files you upload into this collection in the future.

Step 2: Review Impira’s work and see that magic 

By the time you finish labeling Row 1, Impira has already gone through the rest of your rows and files to extract matching data. You’ll see Impira’s predictions populate the queue in just a few moments.

All the rows will be displayed in a list and will feature a red, green, or black marker. These indicate Impira’s machine learning confidence level for that row. Let’s go through and check Impira’s work.

Reviewing Impira’s work will boost confidence and make the machine learning models smarter and more effective. Read more about machine learning confidence at Impira.

  1. Choose any row and take a look to see if all the values are accurate. 
  2. If they need adjustment, click the value and either highlight the correct value on your document or type in the value yourself. Choose Confirm value.
  3. Once all the values are correct, choose Confirm entire row. This signals Impira to go apply new learnings and reprocess predictions.
  4. Continue this process for subsequent rows until Impira grows more confident and turns red markers green.



Step 3: Modify your table

While in File view, hover over the three dots icon in any row and choose, Delete Row, Insert row above, or Insert row below



Now that your table is clean and ready to go, you can Close file view to see that tables in the rest of your files have been extracted. If you still see any more red markers, re-open the file and repeat the review steps listed above to make sure your tables are good to go.

You can also collapse or expand any table by clicking the arrows next to the file name.



Stay in the loop

Get our Release Notes hot off the press, straight into your inbox.

Need more help?

Talk to someone