Image for post
Image for post
Photo by Jakob Owens on Unsplash

How IBM Watson Assistant Is Correcting User Input For Chatbots

And Why Auto Correction & Fuzzy Matching of Entities Don’t Clash

Introduction

There are various methods and approaches to managing a conversation from a chatbot perspective. These can include:

  • Digression
  • Fallback Prompts & Dialogs
  • Graphic Conversational Components
  • Forms / Slot Filling
Demo of IBM Watson Assistant Disambiguation

Correcting User Input

One element the chatbot can use to manage and advance the conversation is by correcting user input without consultation. Obviously there is a fine line here; correcting user input with a relative level of confidence that the correct intent and entity will be targeted.

  • Fuzzy Matching

Auto Correction

Autocorrection, as we all know, corrects words misspelled when a user enters an utterance to the chatbot. Hence, when autocorrection is enabled, the misspelled words in the utterance are corrected on the fly; without user intervention or consultation.

Image for post
Image for post
Activation of Autocorrection within an IBM Watson Assistant Skill
Image for post
Image for post
Example utterance in the test pane with two spelling errors. Automatic correction is applied.
{
"intents": [
{
"intent": "Cancel",
"examples": [
{
"text": "can you please cacnel it"
}
],
"description": "Cancel the current request"
}

Fuzzy Matching

Fuzzy matching needs to be activated within individual entities. This increases the ability of Watson to recognize misspelled entity values.

Image for post
Image for post
Activating fuzzy matching within the entity
Image for post
Image for post
Example of fuzzy matching on the input “christmass daay”

Can Both Be Used In A Skill?

The short answer, is yes…you can use both.

Image for post
Image for post
Left ~ Slight variations in spelling enforces fuzzy matching without autocorrection. Right ~ Bigger variations in spelling invokes fuzzy matching & autocorrection is employed.

Conclusion

When features are enabled within the skill or assistant, it is of essence to understand the ramifications within the conversational environment. Perceived inconsistencies can be introduced which in fact is just a lack of understanding regarding the features activated.

Written by

NLP/NLU, Chatbots, Voice, Conversational UI/UX, CX Designer, Developer, Ubiquitous User Interfaces. www.cobusgreyling.me

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store