Machine Learning

Machine Learning is a branch of AI that lets computers learn by experience.

The breadth of applications for this technology is large and growing. There are several that offer value to smart content creators, as discussed below.

The reason these services are currently grouped under Enterprise features, is they require additional fees. The fees vary according to the size and volume of files/resources scanned. Customization is also required in some cases.

Entity detection

Scan static text to detect people, places, and commercial items.

Scored matches are displayed in a grid. Clicking on a row highlights the term in text.

All editing tools are available. You can replace the term with a dynamic value-of, call-template, or other logic instruction.

Templates screen with Detect entities panel open
Left side shows image of text rotated 90 degrees, right side shows extracted text in Tag

Optical character recognition

Scan an image or PDF file that contains text content. This works even if image quality is poor, or if image is rotated as shown.

An import wizard then converts the scanned text into a start template in Tag ready for editing.

Additional options include detecting form values (e.g., for auto fill) and table content.

Other available models

We're exploring some other Machine Learning applications for use within Tag

  • Topic modeling - scan a collection of documents and establish common themes or subjects (e.g., sports, medicine, politics)
  • Text analysis to detect sentiment (the mood of a document), key phrases, language and syntax (e.g., find nouns and their related verbs)
  • Translation between a wide range of languages
  • Text-to-speech using the same technology as Amazon Alexa
  • Speech-to-text which can be used to transcribe call center calls or other voice recordings into text

How do I learn more?

Contact us for more information about any of the above features.