Updated: Sep 17
This instruction will guide you through the process of creating a plugin in Bitskout to extract data from multilingual documents. We will use a Japanese document as an example to demonstrate the steps involved.
Log in to your Bitskout account and click Create Plugin.
The next step is to click on the Extract button and then choose "From File":
Now we need to load an example. Bitskout needs examples from you to learn what you'd like to extract. Let's load the Japanese Business registry example.
Identify the specific data fields you want to extract from the document. In this example, we will extract the company number and company incorporation date.
Then just add them as they are in the document and put respective values.
You can add additional fields to extract by going to the validation section and specifying the fields you want to extract. Then let's rename our plugin:
Write the correct name:
You can more examples if you'd like. If you are done, please, click Create.
Once you're done with examples, press Create and the plugin will be created. Next, depending on what you'd like to do, choose a tool where you want to use the plugin.
Verify the accuracy of the data extraction by testing it on various forms.
Extracting Data from the Japanese Business Registry
As you can see, we've successfully created a plugin to automate data extraction from a Japanese document. We used only one example and we recommend you add more to ensure the accuracy. It is important to note that there were no coding or technicalities involved. We simply provided the example and Bitskout could figure it out. Try it out on your documents and get in touch if you need help.