You are on page 1of 40

FUnderstanding Conversational Systems

Conversational Prelude
All of us enjoy conversations
What if learning was also conversational?
Gear up to hop on to the world of Bots and Conversational Agents. Hope you
have a good conversation ahead!

What is a Chatbot?

A chatbot is defined as a program that interacts with humans through an interface


and has been designed in a way to mimic response like humans.

It is also known as a Conversational Agent or Dialogue System.

Voice-Based Assistants

I have used Google Now, Siri and Cortana. Are they also chatbots?

Yes, they are also chatbots, specifically voice-based personal assistants.

Origin of a Chatbot
It would be good to understand some history of Chatbots. How did all this
start in the first place?

In 1966, Joseph Weizenbaum devised a simple program named ELIZA, which


was driven by a script and could engage with humans in a conversation. The
conversations of ELIZA matched that of a real psychologist. This program applied
the idea of a pattern matching to question, in order to figure out responses.

First Chatbot Intuition


Chatbot Intuition      
"Humans have the desire to communicate with
computers in much the same way as they do
with other human." - Joseph Weizenbaum

Evolution of a Bot
Science and Engineering should be taught with a little bit of history.
Ok, so how did Chatbots evolve over the years into something that we are
using today?

 Web Interfaces paved the way for Mobile Interfaces. As more and more users
started using mobile apps, service providers started creating native mobile apps.
 Mobile apps became saturated over a period of time as users got tired of installing
and uninstalling them. Only a few prevailed.
 Apps that survived were mostly messaging apps.

 Messaging apps had captured the mindshare of users. This meant that users are
available and responsive via messaging.
 This lead to opening-up of multiple products and services through the chat
platform. A slew of companies started launching their respective chat platforms.
 With the advent of progress made in Natural Language Processing, it became
easier to build conversational interfaces.

Stages of Bot Adoption


Ok. So like mobile and web revolutions in the past, bots have gone through
multiple stages of adoption. What could be the stages of adoption for bots?
Yes for bots, the stages of adoption are similar to web and mobile.

First Stage:
What are bots? Why do we actually need them? Awareness is very low at this
stage.

Second Stage:
We too need a bot interface! Multiple vendors start building and hosting bots.

Stages of Bot Adoption


Third Stage:
Bot First Delivery Model - Bot UI becomes ubiquitous.

Final Stage:
We are bot only. Bots become the new norm or de facto standard.

Personal Bot

So now that we got a peek into the history of bots, what are the various
types of bots available?

Several types of bots are getting developed today. First, you must know
about Personal Bots.

 Personal Bots are messaging bots serving as a personal assistant. An


example would be a shopping bot hosted via Facebook Messenger.
 These bots have a very specific focus and communicate directly with the
users on a one-on-one basis.

Domain Specific Bot


Good to know. What are the other types of Bots?
Hold your horses; you will learn them - one bot at a time. The next type of bots
is Domain Specific.
They represent single service and are very focused on the domain and the service.
For example - Airline Travel Bot is the be-all and end-all stop companion for
all travel related queries from Booking flights, Travel Enquires to Membership
Benefits.

Consumer Bot
Ok. Are there any bots that are chatty and help us stay in touch with our
favorite items?
Yes. Some bots fit that bill. They are called Consumer Bots.
Consumer bots are

 less task-oriented as Business Bots and


 focus more on personal and end user experience.

For example: Mitsuku is a bot built for a Conversational purpose on the Kik


Messenger Platform.

Business Bot
Gotcha. So are all bots just consumer-facing?
You just asked the right question at the right time. Not exactly. There are several
bots for Business Process Functions.
Say you have questions related to HR Policies or Regulation standards.
These bots will guide you through the nuances of the policies in the way you can
comprehend them clearly.

Voice Bots
I am tired of listening about just Chat Bots. Are there any other interesting
bots?
Yes. Voice Bots. All your voice-based personal assistants come under this
category.
Google Assistant, Amazon Alexa, Microsoft Cortana, and Apple's Siri are a
few examples. They take voice commands to execute a specific task.

Super Bots

So, is there a bot of all bots?

Yup. They are called Super Bots.

They are not specific to a Domain or Business Area.


You can ask any question to them on any topic. They respond well if they can find
the answer, if not they admit that it is beyond their understanding.

For example: Google Assistant

Closing Thoughts
I learned a lot about bots so far.
Are there any other types that I should know?
Several bots are getting developed as you read this response.
You could create a new bot of your choice in the future. What you should
understand is
Bots are the new UI.
They can be implemented for any business or consumer-facing scenario.

Anatomy of a Bot

Bots are awesome!

Are you now intrigued to learn more about them? What exactly are bots
made of?

Bots have several parts. Look up to understand what happens behind the scene.

Parts of a Chatbot
That was a well-animated image of a Chatbot. Could you throw more light on
the anatomy of a Bot?
Yes sure. Bot consists of the following parts.

 Human
 User Interface
 Chat Application
 Natural Language Parser
 Component to Trigger Actions
 Responder
Human in the Loop

Why should you consider a human as a part of the chatbot?

Good Question. It is the human who triggers the conversations, and


the response is also directed towards a human. So that is why the user is a vital
component of a chatbot.

User Interface
Why do you need a user interface here?
Another important component is the User Interface (UI).

 UI acts as a medium of communication between the human and the rest of


the components.
 Enough thoughts should go in building a UI that is conducive for
generating a rich experience during conversations.

Chat Application
Yes. I understood the importance of the UI. Can you enlighten me on the
other part of the chatbot?
Next comes the Chat Application on which the bot is hosted. Multiple vendors
provide a platform to host bot.
Facebook, Slack, KiK, etc. are some popular platforms.

Natural Language Parser


A while back, you were mentioning about the advent of NLP so where does
all that happen?
Hold on buddy I am just about to explain that part now. There is a component
named parser that is used to extract the intent and the entity of the input.
Concepts from NLP are leveraged in this component.
Intent and Entity

Now, I get the NLP part but what is the significance of Intent and Entity?

The intent and entity are used to get the context of the conversation and to


trigger the correct action relevant to the question.

Action
I got reasonable clarity on the intent and entity part. So what's next?
After extracting the intent and entity, its time for some action. Based on the context
the right action should be triggered. In some cases, it is an API call, in other
scenarios, it is a DB query.

Responder
You mentioned about the responder, what does that do?
A Responder will respond to the human, based on the response of the action.
This closes the loop.

Closing thoughts
That was cool. Is there anything more that I need to know about the
anatomy?
That is it for now. More in the upcoming topics.

Bot Platforms

Can you give me some information on the various Platforms available for
building and hosting bots?
Yes. Before that, you should understand the various AI as a service providers and
channels.

 Service providers provide a platform for you to build and sometimes host
your bots.
 Once you host a bot, you create a channel for interaction between humans
and bots.

Slack - Business Bot Platform

Can you please share some details about Bot Platforms?

Absolutely. There are multiple platforms available today to build and host bots.
Here, you will be learning only a few of the popular ones. Let's get started with
Slack.

 Slack is a Business Bot Platform available in mobile and desktop.


 You can do a variety of actions with Slack API.
o Post Messages
o Expose Slash Commands
o Expose Clickable Controls
o Event API Subscription
o Administrative Actions

Consumer Bot Platform

Nice. Can we now move on to the next platform?

Sure. Let's move to Facebook Messenger Platform. Facebook is a leading


Consumer Bot Platform with more than a billion active users. Facebook
API provides some really nice features.

 Content Posting
 Check Delivered Callback
 Receiving Messages
 Predefined Button Actions
 Canned Responses
 Sharing Geolocation Information

Voice Bot Platform

Good. Can you explain about the Voice Bot Platforms?

Alexa is a popular bot from Amazon. Alexa is enabled through a device


named Echo. Customization and third-party integration are supported through the
Alexa Skills Kit.

Some of the features include:

 Registering the secondary voice commands for specific actions


 Receiving inputs from clients
 Converse with voice back to user
 Connected Home, integration with IoT devices

Legacy Platforms
Is that all or should I know about any other new platform?
Well there are many new platforms available but don't forget the legacy platforms
for communication like

 Email
 SMS

They are old but still used ubiquitously.

Choosing the Right Platform


Now I am spoilt for choices. How do I choose the right platform?
Good Question. Selecting the right platform is a critical step in building a bot. It is a
tricky process because it is not just a Technology, Business, or Design driven
decision. It is a combination of all of them. Some points to consider before
narrowing down on the platform are:

 Audience: Who are the end users of the bot?


 Use Case: B2B or B2C Scenario
 Features Required: Voice Enabled or just Conversation
 Device Preference

This is not an exhaustive list of points to consider but will help you in choosing the
right platform.

Evaluating the Platform


How could one evaluate the platform?
Build a Proof of Concept (PoC) and get users to converse through the platform.
This is a good way to evaluate your platform.
Just to draw a parallel correlation,
Without habitat, there is no wildlife. It’s that simple. — Wildlife Habitat Canada

Use Case: Conversational Commerce

That was enlightening information on platforms. I now get the hang of things
about bots. I want to understand more about the Use Cases. Can you help
with that?

Let's start with a popular use case, Conversational Commerce.

 Consumers can use a bot to add items to their shopping basket.


 Bots can be used for booking tickets and guide you on your travel itinerary.
 You can also book a cab with the help of your Uber or Lyft bot.

Use Case: Business Functions


Please go on. Enlighten me more on these use cases.
Now You will learn about some Business Functions.
 After the advent of the DevOps way of working, collaboration and
communication are inclining towards ChatOps, i.e., Managing DevOps via
Chat.
 Legal Bots are reviewing Non-Disclosure Agreements and sharing inputs
with the Legal Team.
 Bots are getting leveraged for Corporate Workflow Management.

Productivity and Coaching Applications


Are Business Bots similar to Productivity improvement and Coaching?
Not exactly. For Productivity Improvement actions like:

 Reminders
 Creating to-do lists

specific bots are getting developed.

Coaching is a big area where bots are being leveraged.


For example: Personal bots are being used as trainers for weight loss.

Alerts and Nudges


A while back, you spoke about E-Mail and SMS. Those are age-old means of
communication. Can bots perform similar functions?
Absolutely. Bots cannot completely replace some traditional modes of
communication instead could aid in nudging and alters functions like
 you can get a notification from a bot after you have successfully completed
a financial transaction.
 You can get reminders from bots on some specific goals that you have set
and not progressed.
They act as nudging agents in these scenarios.

Intermediaries
Alright. You have given me some bots related use cases. I am tired of
listening to similar examples. Are there any exciting use cases where bots
are getting leveraged?
Yes. As the human in the loop, bots are now acting as intermediaries between
humans.
 A ride-sharing bot will connect one human to another.
 Travel bots help connect a group of people who are working towards a
similar goal like Mountain Climbing or Deep Sea Diving.

FAQ
That's interesting. I have always felt that the Frequently Asked Questions
(FAQs) could be enhanced with the help of bots. Am I right?
Yes, you are getting there my friend. FAQs are getting replaced by bots for
a better customer experience. Here, bots are acting as the first line of support for
all customer queries.

Closing Thoughts
Thanks a ton. That was very informative.
You are welcome. You would have understood some good use cases by now. Let's
get deeper into the world of bots.

PRIMER QUIZ

Managing DevOps via chat is called chatOps


Google Now, Siri and Cortana can be grouped under:
Alexa a popular bot from Amazon provides feature to integrate with loT devices

Which of the following features cannot be accomplished using stack api?


Bots are the New user interface

Intelligence

Intelligence is the ability to adapt to change —


Stephen Hawking

Artificial Intelligence
So, I have had a perception that Bots are a manifestation of AI. Am I right?
Not exactly. AI is just a significant component of a Bot and not the
essence of a Bot. You are not alone my friend, many have had the same
misconception. I am here to declutter all that.

Artificial Intelligence
So what exactly is Artificial Intelligence(AI)?
According to Wikipedia, "Artificial intelligence (AI) is intelligence exhibited by
machines. In computer science, an ideal 'intelligent' machine is a flexible rational
agent that perceives its environment and takes actions that maximize its chance of
success at some goal".

Source: AI Definition from Wikipedia

Bots and AI
Gotcha. Can you give more insights on this AI part?
AI is not the one-stop shop for building bots; instead, AI is a set of tools and
techniques that can be leveraged to build a conversational system.

Natural Language
Now that I got some clarity on the AI part, let's get into the Natural Language
aspects.
Sure. All conversations happen through Natural Language.

NLU

What is Natural Language Understanding (NLU)?

NLU is a series of steps that take the input text and extract
the intent and entities of the input.

Training
Natural Language is unstructured, how do I make my bot efficient at
extracting intent and entities?

Machine Learning is used extensively to train bots at identifying the various


aspects of Natural Language. Most of the NLP tools come with pre-trained models.

Some Examples
Can you give me some examples of input text?
Say you are conversing with a Travel Bot. You could say,

 "I want to buy a flight ticket to New York", or


 "I want to get flight tickets to New York", or
 "Let us get a flight ticket to New York".

All the three sentences have the same intent, just that they are worded differently.

Grammar
So, do I have to train my bot on Grammar as well?
To a certain extent yes. NLP has a technique called Part of Speech
Tagging which helps understand the construct of the input better.

This, in turn, helps in extracting the entities and intents to perform the desired
action.

Conversation Management
Ok. I have a fair idea on AI and NLU now. What next?
 After understanding the Intent and Entities, it is now time to take action and
respond to the input.
 Dialogue agents have two-way communication, so you have to map a
correct response to the input.

Conversation Management

Can you throw some more light on the Conversation Response?


Managing the conversation has a good amount of AI involved.

 AI component understands the context and renders the correct response


based on the input.
 When there is a lot of context switching, humans handle it better, but
machines find it cumbersome.

Context Switching
Ok. So what are the hardships in switching context?
One word might have different meanings in different contexts.
For example,

 Java is a programming language and a coffee variety.


 Python is a snake and a programming language.

Getting the context is very important to render the correct response.

Semantics
So this is all about getting the semantics right, is that correct?
Absolutely. Conversation Management as a field is still at a very nascent stage. A
lot of progress is required to be made in this field.

Closing Thoughts
Thanks that was insightful. You have changed my perception about bots.
You are very welcome. Miles to go, my friend.

Decision Dilemma
From our previous conversations, I get the confidence that I can develop a
Bot even without AI. Am I right?
Absolutely.
AI is not the de facto component in all bots. You should use it as the situation
demands.

Using AI
In what scenarios should I use AI?
Scenarios that demand

 High use of Natural Language Understanding


 Frequent Context Switching
 Predictive Analytics
 Sentiment Analysis
 Image Recognition

require the use of AI.

Using AI
Got it. So from what I understand, situations where there are many
unstructured components, AI can be used. Am I right?
Yes. Where there is a lot of complexity in the input, AI can help reduce the
complexity.

Not to use AI
What are the scenarios where I need not use AI?
Scenarios where bots

 Send Financial Reports


 Perform News Aggregation
 Send reminders and alerts

do not require any use of AI

Takeaway
So what is the takeaway from this AI conversation?
Well, you must say that if you ask me then

 AI is very expensive so use it cautiously


 AI can sometimes complicate your conversations

so exercise caution before taking a call on AI.

Conversation Types
That was a lot of information on Bot. Now I want to understand more about
conversations. What are the types of conversations that one can have with a
bot?
Ah! So now you want to get into the weeds. Conversations can be broadly
classified into

 Task Led
 Topic Led

Task Led
Can you throw some light on Task Led Conversations?
As the name suggests, these conversations mostly happen with an objective of
accomplishing a specific task. Completing a stipulated task will be the expected
outcome of the conversation.

Example
An example would give more clarity. Can you share one?
Say you are using a bot to order coffee. The successful outcome of conversation
would be taking the order of a coffee.

Coffee Example
Cool. So if I just converse with a bot saying give me coffee, is the task
accomplished?
It is not as easy as you think my friend. People across the globe have a variety of
preferences to order a cup of coffee. So each preference has to be modeled as a
flow-through its entirety.

Modeling Flow
Gotcha. So what exactly happens during each flow?
I think you need some coffee first to be more attentive. Ok, let me not wait until
then.
During each conversation

 the Entities are extracted


 based on the entity, the intent is mapped to each of them.

Sometimes what happens is the conversations go out of context. It is very


important to bring them back to the right context.

Term of the Day

PROCAFFEINATING - The tendency to not start


anything until you have had a cup of coffee.

Topic Led Conversations


Can we move to topic led conversations?
Absolutely. Unlike task led, topic led conversations are long. It depends on the
users' engagement with a specific topic.

More on Topic Led Conversations


So does a chatbot become a chatterbot in topic led conversations?
In a way yes. Topic led conversations can go in multiple directions. They do
not have a well-defined end state. They are more designed to keep the customer
engaged on specific topics.

Example
Again, I am used to learning by examples. Can you share one?
Sure. Say you are conversing with a bot on a movie you recently watched or on
some company you have invested in the stock market. You can converse on
different dimensions on the same topic.

Takeaway
So what I understand is that Topic led conversations are mostly used for
user engagement, and task led conversations are used for business
scenarios. Am I right?
Awesome. High Five. You are getting there.

Segundo quiz

It is advisable to leverage Artificial Intelligence in scenarios that involve


unstructured components
Conversation where ordering a Sandwich through a bot and the bot completing the
activity successfully is a

Conversation where ordering a sandwich a bot and the bot completing the activity
You can build a bot without Artificial Intellgence

Which of the following methologies helps understand the structure of input

What is the series of steps performed to understand the intent and entity of input?
Interacting with Bots
So, is text the only mode of interaction with Bots?
Not exactly, the text is one of the modes of interaction. Some of the ways of
interacting are

 Files
 Audio
 Video
 Emojis
 Buttons

The list goes on...

Files

How can files be used as a means of interaction with Bots?


Say you are interacting with a Tax Filing Bot. Instead of entering all the fields in
your tax filing document, you can just upload the file. Since the data is structured, it
can be easily parsed for further processing.

Files
Now it makes perfect sense. When should I leverage this feature while
designing a bot?
Good Question. Files are used in scenarios where a lot of information has to be
processed, and your chat window is small to accept all that information in one go.
You can also use them when you have tables.

Audio
Can you throw some light on Audio Interactions?
Sure. For personal assistants like Google Assistant, Siri, Amazon Alexa, etc. the
mode of interaction is Voice. This type of interface is called Vocal User
Interface. You trigger commands like Ok Google "How is the weather in New
York?" and you get a response back with the required details.

Audio
That was useful. But how do we address the accent issue with voice
interface?
Good question. Voice might not be a useful interface in every scenario. Voice is
recommended only for private interactions. A lot of training is required to get the
bot to understand various accents.

Video
Now I understand how Audio interactions happen. I am really intrigued about
videos. Can you help?
Sure. Video interactions happen in the following scenario. Say you are interacting
with a bot to troubleshoot a specific problem and you need an approach. Your bot
can respond with a video that will help you troubleshoot the problem. This is one of
many scenarios where videos can be used as a means of interaction.

Emojis
Somewhere above, you did mention emojis as means of interaction? Is that
the way forward in terms of communication?
Not exactly. Emojis are more of reactions to conversations. These reactions can
also be used to take actions, acknowledge, and respond.

Emojis

Can you give me some example of how Emojis are used for conversations?

Sure. Look at the image above. The same conversation can be reacted with emojis
and expressed with the help of emojis.

More on Emojis

Is that all? Any interesting examples?

Yes. Look at the image above. You can create polls and get a response from
emojis. You can also aggregate the response and perform analytics using those
numbers.

Buttons

That was insightful. Can you now talk about Buttons?

Yes. Buttons are a wonderful way to navigate a conversation. You can confine the
user to a pre-defined set of responses and guide the user in the desired direction.

Buttons
So should I use buttons only for canned responses?

Not just for Canned Responses. It can also be used for other scenarios. Look at
the image above. You want to collect orders based on some predefined inputs.
You can leverage buttons in those scenarios.

Takeaway
Thanks a bunch. It was an eye-opener for me knowing so many more ways of
interacting.
You are very welcome my friend.

Context

I have been intrigued by this thought on how a bot understands the context.
Can you throw some light on that?

Roger that. Say you are in a conversation with a Travel bot. You are chatting about
the Eiffel Tower. The conversation goes as shown in the image above.

In the above conversation, it refers to Eiffel-Tower the context of the discussion.

This can be achieved with sufficient training on varied topics to understand the
context.

Context

Got it. Although there was never a mention of the Eiffel Tower in the
following questions, the word  it specifies the context. Am I right?

You are getting there my friend. Let us take another example. Look at the image on
the top. You will get more clarity on the intent and context.

Context and Intent


I saw the travel booking example in the previous card, but I am still unclear
on how to train a bot on the context and intent. Can you help to clarify?
Sure. Some of the variables in the conversation have limited scope like start and
end date; some have a global scope like User Information. These variables are
tightly coupled with the intent and context of the discussion.

Context and Intent


Why are Context and Intent so Important?
Bots are normally used to a request to response setup. They should not time out
after multiple conversations and should remember the context from the beginning.

Context and Intent

I still feel there is an overlap between Context and Intent. Can you please
help me clarify?

Look at the Image above. Hope you got the answer to your question.

Getting the Context


Are there some tips and tricks to get the context right?
Yes. You can get the context from

 Pronouns
o Words like "it", "this", "hers", and "his" are pointers for getting the
context.
 Rich Controls

Memory
I got the hang of what context and intent are for a Bot. How different is a
memory?
Memory is generic when compared to context. Here, a bot should be able to pull
intents at various time steps and take actions.

Amnesia
Do bots suffer from Amnesia?
If you do not train them well, then they can suffer from Amnesia.

Closing Thoughts
That was very informative. Now I have some clarity on Context and Memory.
Very Good. Getting a bot to understand the context and memory is one of the most
challenging parts in designing a bot. It is also a good area of growth from a
technical standpoint.

Human In the Loop


So far, I have understood multiple aspects of building bots and enabling
conversational experience. Is there anything additional I have to know?
Yes. You should understand a very important aspect of building conversational
systems i.e. Human-in-the-loop.

Humans or Bots

Ok. So, are humans going to work with bots or humans going to replace
bots?

To say the truth, It is a little bit of both.

HITL
I am getting confused now. Can you help me understand this concept?
Sure. The steps to handle Natural Language Understanding are Understand ->
Act -> Respond.
Let us take an example: You ask a bot

“What’s the status of SE 123?”


Decomposing the above question
 Understand: User wants to understand the flight status of Flight SE 123.
 Act: Query Database or Hit API to find the flight status.
 Respond: Reply based on the output received from the previous step.
Having a human intervention in any of the above steps is called Human-In-The-
Loop.

Human Intervention
When should Humans Intervene in this process?
Humans should intervene when

 Algorithms find it difficult to understand new scenarios


 Algorithms have no clue how to perform a certain action
 Unsuccessful actions
 Input is out of scope

Best Practices
Are there any best practices for this scenarios?
Well, nothing is written in stone, but a few good practices can make things better if
implemented correctly.

 Data Collection should be done properly


 Gauging possible outlier scenarios and include them during training
 Handling exception scenarios should be thought out well.

The Story So Far ...


I am overwhelmed. I felt that I learned a lot. Is that all?
Well, you have barely scratched the surface. But let us play back what you
learned.

 Understood the definition of a Bot and some History


 Architecture and Parts of a Bot
 Various platform to build and host bots
 Natural Language Understanding, getting the intent and context right
 When to use and when not to use Artificial Intelligence?
 Conversational Experience, i.e., Task Led and Topic Led
Conversations
 Rich Interactions, using other means of Interactions
 Importance of Memory and Context
 Human in the Loop

Hope you enjoyed learning! May the force be with you when you build a bot!

Closing Thoughts ...


Thank You . That was a good conversation.
You are very welcome.
Are you referring to the dialogue from the movie "The Last Samurai" ??? ...

QUIZ FINAL:

Pronouns in sentences can be used as indicators for context

Google Now, Siri and Cortana can be grouped under


Humans should interfere when the inputs go out of scope for a bot

Managing DevOps via chat is called chatops


Buttons are used for rendering canned responses:

What was the methodology used by ELIZA the program devised by Joseph..
What type of Bot is Mitsuku (Bot builf for conversational purpose on KIK manager
Plataform
You can create polls and get responses to polls using emoji

Natural Language is structured data

What type of interface do Google Now, Alexa, Siri Use?


Natural Language Parser is used to extract ___ and ___wso

Files in some specified format can be used to interact with bots


Which of the following features cannot be accomplished using slack api?

Alexa, a popular bot from Amazon provides feature to integrate with IoT devices
What is the order of steps in Natural Language Understanding?

Which of the following features can be accomplished with the help of Facebook
Messenger Plataforms?

You might also like