Taking your
chatbot to the next level

Taking your
chatbot to the next level

Taking your
chatbot to the next level

Taking your
chatbot to the next level

Taking your
chatbot to the next level

Using Natural Language Processing and knowledge bases

Using Natural Language Processing and knowledge bases

Using Natural Language Processing and knowledge bases

Gergely Havlicsek, Product Owner, g.havlicsek@mito.hu 
July, 2020 · 5 min read

How can you evolve a chatbot?

Reacting to
certain
keywords

Reacting to
certain
keywords

Reacting to
certain
keywords

arrow_to-right_80px

?

arrow_to-right_80px

1on1
personalized
messages

1on1
personalized
messages

1on1
personalized
messages

There are two indespensable components

1. Natural Language Processing

To be able to understand users contextually

2. Knowledge base

Providing relevant, easily searched answers for a chatbot

What is Natural Language Processing?

NLP is a process where we recognize intents (verbs, activities that the user wants to do) and entities (content for the action that needs to be performed) from the user inputs, chat messages.

The world has changed a lot in 2020: the availability of products and services and the service channels used have all undergone a transformation. Usual activities might not be carried out the usual way anymore; the behaviour of customers has become different.

So structuring unstructured data and giving back useful information to the user, requires a systematic approach in each step of the process.

The world has changed a lot in 2020: the availability of products and services and the service channels used have all undergone a transformation. Usual activities might not be carried out the usual way anymore; the behaviour of customers has become different.

Intents

Intents

Intentions of the end-user, which are conveyed by the user to your bot.

  1. Casual Intents
    ‘Hi’ or ‘Thanks for talking to me’
  2. Business Intents
    ‘What are your opening times?’ or ‘Is parking free?’

Intent Samples

Intent Samples

Use real discussions to train your bot besides manufactured and generated samples

Responses

Responses

Based on intent recognition the tone of voice and the flow is selected

How to use knowledge bases?

Knowledge base integration with chatbot systems can be done on different levels, determined by the needs and use cases. Starting with simple search queries for relevant data you can advance the capabilities of your knowledge base integration to reach higher levels. 
Eventually combining the advantages of NLP and Knowledge Bases.

Fundamentals of effective knowledge bases

1. Properly functioning search system

2. Stable and effective backend storage system

2. Stable and effective backend storage system

3. Simple archive and categorization system

4. Good integration capabilities

5. Analytics and reports

What is our approach?

Be practical and scalable

We focus on topics suitable for NLP which then can be scaled with the help of a knowledge base.

NLP Model Training

Possible solution:
Handling the 5 most frequent questions with a chatbot in customer service

Possible solution:
Handling the 5 most frequent questions with a chatbot in customer service

Possible solution:
Handling the 5 most frequent questions with a chatbot in customer service

Our own methodology of NLP training follows a step-by-step cyclical process which is similar to agile programming. We put strong emphasis on creating a stable working model at the start and improving on it throughout the life of the project.

A systematic approach

Every step has its own challenges and best practices, and we believe that a systematic approach can help us deliver the needed expertise at every step of the journey

But most importantly

Identify intents in advance

Differentiate between general/casual and business intents.

Train intents with original conversations

Otherwise train with manufactured utterances. Minimum 5, optimally 10 utterances.

Train - Converse - re-train

The feedback loop must continue in order to train your NLP models.

What can be expected?

1-3 months

Setup

Setup

Setup

Identification of 5 most common topics, which are most suitable for NLP

3-6 months

Iteration

Testing and iterating on original scope based on real conversations

6-12 months

Feature development

Enough data is available to re-cluster topics and iterate feature development roadmap

How to decide?

Business

Are you operating a large scale customer service with main clusters of recurring questions / topics in high volume?

Technical

How easy is it to integrate a new solution to your customer journeys and potential business backend systems?

Why?

Easy to start and collect feedback

Easy to start and collect feedback

Highly scalable solution

Highly scalable solution

A huge step
towards 1on1
personalization

A huge step
towards 1on1
personalization

Mitobot_illu2

Would you like to learn more?

Want to know more about our chatbot solution?

You can find everything in one place here:
mitobot.io