The importance of test, measure & improvement in chatbots and NLP by Grant Ronald


Those of you of a certain age might recognize the above image – the TV test card: played whenever a channel was “off air” and used for calibration. Whilst this might represent an image of a time-gone-by, the concept of measuring against a known baseline is one we can all recognize and is particularly important for those of us developing chatbots/digital assistants.

At Oracle I run a team that whilst part of the development organization that build our conversation AI platform (Oracle Digital Assistant), we also build production chatbots using that platform (we are the team who eat the dog food!). And in one of our current projects we took the time to re-visit our initial language training data to see whether the lessons we’ve learned, and documented (below) had a measurable difference on the “intelligence” of our digital assistant. Read the complete article here.

Developer Partner Community

For regular information become a member in the Developer Partner Community please register here.

clip_image003 Blog clip_image005 Twitter clip_image004 LinkedIn image[7][2][2][2] Facebook image Meetups

Technorati Tags: PaaS,Cloud,Middleware Update,WebLogic, WebLogic


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.