Image for post
Image for post

La creación de prototipos iterativos es útil para desarrollar aplicaciones de inteligencia artificial conversacional.

Image for post
Image for post

Introducción

Comenzar con los chatbots en particular y la IA conversacional en general puede ser abrumador. Es posible que haya oído hablar de los chatbots y tenga una comprensión básica de la esencia. Y ahora el siguiente paso es comenzar construyendo algo … pero ¿cómo?

Image for post
Image for post
https://rasa.com/docs/rasa/playground

Las preguntas que se hacen con frecuencia incluyen:


Image for post
Image for post
Photo by JuniperPhoton on Unsplash

Extract Fixed, Closed Sets of Related Words With Synonyms

Introduction

There are a number of entity types which are available across chatbot frameworks, one of these are lists.

Lists are less glamorous than ML entities, entities with roles or composed entities. However, lists serves a specific purpose and there will most probably always be an implementation use-case for it.

Lists are used when you are looking for specific entities within an user utterance. Ideal scenarios are when you have a finite list of items, which might include:

Normalization adds consistency to the result yielded… For instance entries like john, Johnny, John, Jonh can be all normalized to Jonathan. …


Image for post
Image for post
Photo by Carl Nolting on Unsplash

Build A Chatbot with Microsoft Bot Framework Composer & Composite Entities

Introduction

Even though most NLU tools converge on the same basic principles for entities and intents, when it comes to developing the dialog various approaches are followed.

With creating the state machine or managing the dialog nodes, four distinct approaches are currently followed in the chatbot marketplace for dialog creation and management.

Bot Framework Composer falls into the category of Dialog Configuration.

The holy grail is to have a composer or design environment where the call-flow can be designed graphically and simultaneously create executable code.

Or least a design which can be imported into a chatbot framework and executed. …


Image for post
Image for post
Photo by Hassan OUAJBIR on Unsplash

Surface The Power of LUIS Composite Entities Via Composer

Introduction

Even though most NLU tools converge on the same basic principles for entities and intents, when it comes to developing the dialog various approaches are followed.

With creating the state machine or managing the dialog nodes, four distinct approaches are currently followed in the chatbot marketplace for dialog creation and management.

Bot Framework Composer falls into the category of Dialog Configuration.

The holy grail is to have a composer or design environment where the call-flow can be designed graphically and simultaneously create executable code.

Or least a design which can be imported into a chatbot framework and executed. …


Image for post
Image for post
Photo by Andre Benz on Unsplash

Improve Your Chatbot’s Ability To Understand Customers With A New Intent Detection Model

Introduction

IBM Watson Assistant is introducing new functionality at a remarkable cadence. Notably these changes are not disruptive to existing features and augment or compliment existing functionality.

The previous big announcement from Watson Assistant was Actions…prior to the enhanced intent detection model.

November 2020 IBM Watson Assistant released a beta version of their new intent detection model. Intents are the frontline of any conversational interface.

Intents are categories of what users’ intentions are; really the frontline of any chatbot. Accurately classifying the user utterance according to an intent is of utmost importance.

Image for post
Image for post
Under Skill Options in IBM Watson Assistant the new feature is visible.

Various parameters can be set in each dialog node to determine relevance, and the most popular measure here is intent scores. …


Image for post
Image for post
Photo by Ann Fossa on Unsplash

Chatbot Dialog Design & Development Are Settling Into Four Main Categories

Introduction

When different vendors and platforms converge on the same basic approach & principles, it is safe to assume it is the most efficient way of doing it.

Looking at the large and emerging chatbot platforms, they all converge on two key aspects:

There are elements like form or slot filling, policies etc. which is also important. But for the purpose of this story, we will not focus on it.

Intents

Intents are usually defined with by a description and a few training or utterance examples.

Image for post
Image for post
Rasa Chatbot Framework: intent example with contextual entities defined.

The utterance examples are what a user is anticipated to say or state. …


Image for post
Image for post

10 elementos de un proceso conceptual para derivar reglas y conceptos conversacionales generales

Image for post
Image for post
Photo by Kaspars Upmanis on Unsplash

Introducción

Al crear o, más bien, elaborar una conversación de chatbot, nosotros, como diseñadores, debemos inspirarnos y orientarnos en las conversaciones del mundo real.

Image for post
Image for post
Naturaleza muerta del pintor holandés Henk Helmantel. Encontré ver sus pinturas en la vida real discordante. Sabes que es una abstracción de la realidad, pero que parece real.

Los elementos de la conversación humana deben identificarse y resumirse para incorporarlos en nuestra conversación de chatbot.

Las reglas y conceptos generales de las conversaciones humanas deben derivarse e implementarse a través de medios técnicamente astutos.

A continuación, enumero 10 elementos de la conversación humana que se pueden incorporar en una interfaz de IA conversacional. …


Image for post
Image for post
Photo by Krisztián Korhetz on Unsplash

And How Does CX Compare To Other Environments…

Introduction

Looking at a previous Medium story wrote on Dialogflow, which is now referred to as Dialogflow ES, the one big issue I raised is the lack of a dialog development and management environment.

Image for post
Image for post
Google Dialogflow CX Main Console

And, that ES will have to be used as an API with native code managing the dialog and state management.

This has been solved for with Dialogflow CX.

In other words, an interface where the state of the conversation can be managed.

Currently, in the market, there are five distinct groupings in approaching dialog design and development…

Dialog configurations, design canvas, native code, ML stories and of course design canvas. …


Image for post
Image for post

Las acciones o “Actions” son nuevas en Watson Assistant… Hoy te enseño lo que he aprendido al usarlas.

Image for post
Image for post
Photo by David Monje on Unsplash

Introducción

Se ha agregado una nueva característica a IBM Watson Assistant llamada Acciones. Esta nueva característica permite a los usuarios desarrollar diálogos de manera rápida.

Image for post
Image for post
Mover pasos en una acción para alterar la secuencia de eventos conversacionales

El enfoque adoptado por IBM con Actions es de naturaleza extremadamente no técnica. La interfaz es intuitiva y prácticamente no requiere conocimientos de desarrollo ni formación previos. Las variables de entrada del usuario (entidades) se recogen automáticamente con una referencia descriptiva.

Los pasos de la conversación se pueden reorganizar y mover libremente para actualizar el flujo del diálogo.

Las actualizaciones se pueden guardar automáticamente, el aprendizaje automático se lleva a cabo en segundo plano.

Y la aplicación (acción) se puede probar en un panel de vista previa. …


Image for post
Image for post
Photo by Beeline Navigation on Unsplash

An Enhanced Environment for Telephony, Collaboration, Design Canvases And More

Introduction

Currently Google offers three chatbot or Conversational UI development environments; Actions SDK, the familiar Dialogflow ES (Essentials) and the newly added Dialogflow CX (Customer Experience).

In principle, the main differences between ES and CX are:

Image for post
Image for post
Image for post
Image for post

Cost

From the two tables below, detailing cost, it is evident that the cost of running CX is exorbitant, to say the least. The only explanation I can think of, is the fact that CX is aimed at an enterprise environment and implementation.

Where ES often serves as a starting point for individual users. …

About

Cobus Greyling

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