tekom - conferences

Take your DITA game up a notch with NLP scripts

  • Tutorial
  • Content Strategy & Information Architecture
  • 06. November
  • 09:00 - 10:00 AM (CET)
  • C7.3
  • Mr Gyanesh Talwar

    Mr Gyanesh Talwar

    • ServiceNow

Contents

We are presenting a method to enhance client-side content quality checks using Python Natural Language Processing (NLP) libraries. Leveraging the symantec precision of DITA elements along with easy Python NLP constructs, you can build checks that ensure your content quality meets predefined standards. For example, using scripts like CheckDITAContentSuitabilityCMD from TheContentGym, you can verify if Step > CMD element content uses action verbs correctly. This automated approach allows you to execute checks on thousands of files in seconds, detecting anomalies and errors that would otherwise take days of manual effort to uncover. This solution significantly improves efficiency and accuracy in content validation processes.

Takeaways

Learn to build client-side content quality with NLP libraries that check DITA content quality. Quickly build scripts to audit thousands of DITA files, ensuring action verb usage and detecting errors in seconds.

Prior knowledge

A little python - If you are able to install python and run hello world, you are good..

Speaker

Mr Gyanesh Talwar

Mr Gyanesh Talwar

  • ServiceNow
Biography

In his two-decade-long career, Gyanesh Talwar has led DITA- and FrameMaker-adoption efforts, designed the ACE certification exam for Adobe FrameMaker, and is passionate about simplifying complex concepts. He explores new technologies in user and developer documentation.