What's up all-stars,
My client is a repair service who has a poorly constructed database when it comes to data trending (lots of free text fields). While I'm working with them on normalizing their data, they want to be able to do trending on their years of previous sentence-format information. Does anyone know how to do part-of-speech tagging and grammatical parsing in excel or can anyone otherwise point me in the right direction?
For example, these sentences
The capacitor failed due to dielectric breakdown.
Faulty capacitor (dielectric breakdown).
The cap is bad. Appears to have suffered dielectric breakdown.
would all yield the same data:
PART FAILURE_MODE
capacitor dielectric breakdown
capacitor dielectric breakdown
capacitor dielectric breakdown
Bookmarks