Image for post
Image for post
Photo by Ma Fushun on Unsplash

Iterative Prototyping Is Useful In Developing Conversational AI Applications


Getting started with chatbots in particular and Conversational AI in general can be daunting. You might have heard about chatbots and have a basic understanding of the gist. And now the next step is to get started by building something…but how?

Image for post
Image for post
Rasa’s Prototype Training Indicator.

Questions often asked include:

  • How do I access the software?
  • Do I need a GPU or extensive computing power?
  • Will it be expensive?
  • Do I need a specific design or prototyping tool?
  • How do I gather training data?
  • Does only the big players have what I need; i.e. Google, Facebook or AWS?
  • Where and how do I host my bot? …

Image for post
Image for post

Calcula cuál es el esfuerzo que lleva a cabo el cliente a la hora de resolver sus dudas con tu chatbot.

Image for post
Image for post
Photo by Robert Tjalondo on Unsplash


  • ¿Qué es el customer effort o esfuerzo del cliente y cómo se puede medir en las conversaciones de los chatbots?
  • ¿Y cómo puede la desambiguación mejorar este concepto?
  • ¿Se puede emplear el aprendizaje automático para mejorar el esfuerzo del cliente con el tiempo?

Aquí veremos tres elementos, que combinados tendrán un gran impacto en la experiencia de conversación que estás construyendo:

  • Desambiguación.
  • Aprendizaje automático.
  • Esfuerzo del cliente.
Image for post
Image for post

¿Qué es la desambiguación?

En la parte inferior de esta página hay enlaces a artículos detallados sobre desambiguación. Sin embargo, os dejo un resumen…

Cuando un usuario ingresa una utterance ambigua, en lugar de mostrar por defecto la intención con la puntuación más alta; el chatbot comprueba las diferencias entre las puntuaciones de intención más altas. …

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

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


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

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

These elements have something in common…

All of these elements are employed as part of an active dialog exchange between the user and the chatbot. Hence it involves the user.

One element which can be implemented which does not require user involvement is detecting anomalies in user input and automatically correcting user input prior to issuing the input to the NLU.

In this story I am looking at autocorrection and fuzzy matching. And why the two do not…


Cobus Greyling

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

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