GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Version
Recent Updates
Previous Versions
Deprecations
Request a Feature
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Dynamic Intent Node
GenAI Node
GenAI Prompt
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Terminology
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
LLM and Generative AI Logs
NLP Insights
Task Execution Logs
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Team Collaboration
Plan & Usage
Overview
Usage Plans
Templates
Support Plans
Invoices
Authorization
Conversation Sessions
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
HOW TOs
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Composite Entities
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Intent Scoping using Group Node
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Natural Language
  5. Knowledge Graph Training

Knowledge Graph Training

Training your Assistant is not restricted to the Machine Learning and Fundamental Meaning engines. You must also train the Knowledge Graph (KG) engine, too.

The Ontology-based Knowledge Graph turns static FAQ text into an intelligent, personalized conversational experience. It uses domain terms and relationships thus reducing the training needs. It also has the capability to enable the ontology weighted features whenever ML gets confused and to automate conversational dialog for resolving appropriate answers.

The Few-Shot Knowledge Graph leverages Kore.ai’s LLM and lets you add FAQs without building an ontology. Less training and maintenance are required since you do not need to configure the graph term-by-term. Learn more about Knowledge Graph Types.

The Knowledge Graph engine thus responds to users’ intents by identifying the appropriate questions within the Knowledge Graph, and then presenting the user with the appropriate response.

You can find the Knowledge Graph by selecting your desired VA, then going to Build > Conversation Skills > Knowledge Graph.

Training a Few-Shot Knowledge Graph

Few-Shot Knowledge Graphs do not require an ontology and do not perform path qualification. Instead, they identify intents using semantic similarity and pattern recognition. However, if you want to train the VA on a specific use case for which the appropriate FAQ is not identified, you can map FAQs to an ontology, similar to what you would do with an Ontology-based Graph.

The main difference concerning training is that in the Few-Shot KG, Terms don’t require some of the training configurations needed in an Ontology Graph.:

  1. Default Terms are not available. The only exception is when you switch from an Ontology Graph, in which case existing Default terms are stored as such until updated. Afterward, Default terms become Organizer terms and can be set as Mandatory.
  2. Organizer Terms do not support Path-Level and Knowledge Graph Synonyms. They support Intent Preconditions and Context Output. 
  3. Mandatory Terms support Traits, Path-Level and Knowledge Graph Synonyms, Intent Preconditions, and Context Output, just like in an Ontology-based Graph.

You can set all Thresholds and Configurations except Path Coverage and Lemmatization using Parts of Speech, Search in Answer, and Qualify Contextual Paths, which are not supported by Few-Shot Graphs. 

See the Knowledge Graph Types Comparison Table for a detailed list of supported features.

Also, see Training Configuration below for training setup details.

Knowledge Graph Engine Capabilities

The following are the overall capabilities of the Knowledge Graph Engine:

  • Ease of Training using Synonyms: Kore.ai’s Knowledge Graph has a provision to associate synonyms against a graph node. This helps capture the variation in a question. For example, flight can be used as a synonym for plane in an FAQ such as How can I buy a plane ticket?.
  • Better Coverage with Alternate Questions: The Knowledge Graph has a provision to add alternate questions. This helps us to capture the various ways a user might ask the same question. For example, in How do I change my flight? we can add an alternate question as Can I change my flight?.
  • Improved Accuracy: Ontology-driven question-answers reduce the possibility of false positives.
  • Weighing Phrases using Traits: Kore.ai’s Knowledge Graph engine includes a concept of traits for filtering out irrelevant suggestions. See here for further details.
  • Ability to Mark Term Importance: The Knowledge Graph has a provision to mark that an ontology term is important. For example, in the question, How to book a flight, the word flight is an important term. If the flight keyword is not present in the user utterance, then it makes little sense.
  • Ability to Group Relevant Nodes: As the graph grows in size, managing graph nodes can become a challenging task. Using the organizer node construct of the ontology engine, developers can group relevant child nodes under a parent node.

FAQ Detection Steps

Here are the steps that the Knowledge Graph Engine takes when detecting FAQs:

  • Step 1: Extract Nodes: The KG engine processes the user utterance to extract the term (ontology nodes) present in the graph. It also takes into consideration the synonyms, traits, and tags associated with the terms.
  • Step 2: Query Graph: The KG engine fetches all the paths that consist of the extracted nodes.
  • Step 3: Shortlist Paths: All the paths consisting of 50% or more matching terms with the user utterance are shortlisted for further processing.

    Note: Path coverage computation doesn’t consider the root node.
  • Step 4: Filter with Traits: If traits are defined in the Knowledge Graph, paths shortlisted in the above step are further filtered based on the confidence score of a classification algorithm in user utterance. 
  • Step 5: Send to Ranker: The KG engine then sends the shortlisted paths to the Ontology Ranker Program.
  • Step 6: Score based on Cosine Similarity: The Ontology Ranker makes use of user-defined synonyms, lemma forms of word, n-grams, stop words, to compute the cosine similarity between the user utterance and the shortlisted questions. Paths are ranked in non-increasing order of cosine similarity score.
  • Step 7: Qualify Matches: The Ontology Ranker then qualifies the paths as follows:
    • Paths with score >= upper_threshold are qualified as an answer (definitive match).
    • Paths with lower_threshold < score < upper_threshold are marked as suggestions (probable match).
    • Paths with a score < lower_threshold are ignored.

Training Guidelines

From the Knowledge Graph, follow these steps to build and train the corresponding Knowledge Graph:

  1. Identify terms by grouping the unique words in each FAQ question. Build a hierarchy based on all such unique words.
  2. Ensure that each node has not more than 25 questions.
  3. Associate traits with terms to enable filtering FAQs from multiple identified results.
  4. Define synonyms for each term/node in the hierarchy. Ensure that all the different ways to call the term are defined.
  5. Depending on the importance of each term in a path, mark them as either mandatory or regular.
  6. Define alternative questions for each FAQ to ensure better coverage.
  7. Manage context for accurate response.
  8. Use Stop Words to filter unwanted utterances.

Training Configuration

This article presupposes that you already know the basics of building your Knowledge Graph. If not, please read this article.

In order to configure the training of your Knowledge Graph for improved VA performance, we recommend that you go through as many of the following parameters as possible. These parameters involve:

  • Adjusting the Term Type to your VA’s needs when adding terms to your graph,
  • Setting tags for FAQs to improve detection,
  • Configuring synonyms for Knowledge Graph terms to enhance path detection and help the VA find the appropriate questions to answer by widening the spectrum of words that can be used to find a specific question,
  • Adding Traits to detect relevant information that improves intent or scenario detection.
  • Manage Context to help users complete tasks faster and create more natural, human-like back and forth conversations.
  • Add Stop Words which will be discarded from intent scoring, even when they are a node term. 

Moving forward, we will discuss these parameters in detail.

Term Type

Designate the terms and tags in the Knowledge Graph as Default, or Mandatory, or Organizer depending on their importance in qualifying matching paths: You can configure term types by accessing the term/node settings.

The available term types are: 

  • Default: Default terms do not have any particular considerations in shortlisting qualified paths.
  • Mandatory: When you mark a term as Mandatory, all paths associated with the term are shortlisted for ranking only if the user’s utterance includes the mandatory term or its synonyms.
  • Organizer: Term can be marked as being a part of the Knowledge Graph only for organizing questions (this option is available only for terms, not tags).

Tags

When you type a question in the Intent Name Add Question field, the Knowledge Graph suggests some tags that you can add to the graph based on the text. To include a suggested term to the path, select the tag from the drop-down list that appears when the cursor is in the Add Term field. You can also add custom tags by typing them in the add term field and hitting the Enter/Return key.

After you add a tag, it is visible below the question like a tag everywhere the question appears. Tags work exactly like terms but are not displayed in the Knowledge Graph to avoid clutter. 

Synonyms

You can add multiple synonyms for each term in your Knowledge Graph, making the path discoverable for varied user utterances. You can add synonyms for a term from the term’s  Settings window.

When you add a synonym for a term in the Knowledge Graph, you can add them as local (Path Level) or global (Knowledge Graph level) synonyms.

Local Synonyms apply to the term only in that particular path, whereas Global Synonyms apply to the term even if it appears on any other path in the hierarchy.

To add synonyms for a term, follow the below steps:

  1. On the top left of the VA’s Knowledge Graph, hover over the node/term for which you want to add synonyms.
  2. Click the gear icon to open the Settings window.
  3. To add synonyms,  do the following:
    1. To add local synonyms, type them in the box under Path Level Synonyms.

    2. To add Global synonyms, click Edit then Add under Knowledge Graph Synonyms and enter them.
      Note: Press Enter after typing each synonym in the Synonyms box. If you type multiple synonyms without pressing Enter after each synonym, all the synonyms are considered as a single entity, even if they are separated by spaces.


       

      Note: These Knowledge Graph Synonyms can also be accessed from the Manage Synonyms option under the more options icon on the top-right of the Knowledge Graph page.


       

    3. You can use Bot Synonyms in the identification of KG terms. This option can be enabled either from the Threshold and Configurations or from More Options > Manage Synonyms.

      Once enabled, the bot-level synonyms that match with KG terms (or tags) are automatically displayed under the Bot Synonyms heading in the Synonyms section and are used by the KG engine. The Bot Synonyms are used similar to that of KG graph level synonyms, for path qualification and for question matching. When a node matches both with a bot synonym and a bot concept, the bot concept takes priority.
    4. To add synonyms for a child node, enter them in the Synonyms box next to the Child Terms listed at the bottom of the settings window.


Traits

You can create traits with common user utterances and then add them to the relevant terms in your Knowledge Graph. To know more about Traits, click here.

Traits are common across the XO Platform. If you have created Traits from the Natural Language section they are available for use here as well.

To create a trait, follow the below steps:

  1. On the top-right of the Knowledge Graph window, click the more options icon and then select Manage Traits.

  2. On the Manage Traits window, click New Trait.
  3. In the Trait Type and Trait Name field, enter a relevant name for the trait. For example, Flight Fare.
  4. In the Utterances field, enter all the utterances that you want to include in the trait. Examples of the Issues trait: First Class, Premium Economy, Economy, etc.
  5. Click Save & Add Rule or Save & Exit.

After you create a trait, you can assign it to multiple nodes in the Knowledge Graph.

To add a trait to a node/term, follow the below steps:

  1. On the top-left of your Knowledge Graph, hover over the terms to which you want to add the trait.
  2. Click the gear icon to open the Settings window.

Select the name of a trait from the Trait drop-down list and click Save

Note: Adding a trait to a node doesn’t add it to other nodes with the same name. You must add traits to each relevant node separately.

Context

You can Manage Context for the terms and tags by setting:

  • Intent Precondition – the context that should be present as a qualifier for this node or tag
  • Context Output – the context that should be populated to signify the execution of this task

Post the release of v8.0 of the Platform, context can be enabled for Organizer nodes as well. Enabling the Manage Context option allows you to set the context precondition and context output mentioned above. Click here for more on Context Management.

Note: Enabling the Manage Context option will not emit the term/node name by default.

 

Stop Words

Stop words present in the user utterance are discarded for scoring even if the stop word is used to define a node (or node synonyms).

The Knowledge Graph has a language-specific predefined set of stop words. This list can be customized to suit your requirements.

To edit the stop words list, follow the below steps:

  1. From the Knowledge Graph page, click on the more options icon and select Manage Stop Words.
  2. From the Manage Stop Words window, delete or add stop words.

Training Process

After you complete creating/editing the Knowledge Graph, click the Train button on the top-right of the Knowledge Graph window. When you perform this action, all the paths, synonyms, and question-answer sets are sent to the Graph DB engine.

Note: After every change that you make to the Knowledge Graph such as adding synonyms to a term or editing the name of a term, you must click the Train button for the changes to reflect in the bot responses.

 

The training fails if any single node has more than 100 questions. This limit was introduced in v7.3 to make the Knowledge Graph more efficient by improving the response times. In such failure cases, you can Download Errors CSV file which lists the path with more than 100 questions. You can use this file to rectify your Knowledge Graph.

Testing

When you complete creating the Knowledge Graph and training it, we recommend that you interact with the assistant and ask questions connected to the Knowledge Graph. Test the responses by using a variety of utterances so that you can identify missing terms, questions, alternative questions, synonyms, and traits. Learn more about utterance testing.

Thresholds & Configurations

To train and improve the performance, Thresholds and Configurations can be specified for all three NLP engines – FM, KG, and ML. You can access these settings from Natural Language > Training > Thresholds & Configurations.

Note: If your VA is multilingual, you can set the Thresholds differently for different languages. If not set, the Default Settings will be used for all languages. This feature is available from v7.0 onwards.

 

The settings for the Knowledge Graph engine are discussed in detail in the following sections.

Explore Thresholds and Configurations

To navigate to Thresholds and Configuration, please follow the steps below: 

  1. Open the VA for which you want to configure Knowledge Graph settings.
  2. Hover over the left pane and click Natural Language > Training.
  3. Click the Thresholds & Configurations tab.
  4. Below is a detailed discussion about the Knowledge Graph section on this page.

Here are the features that you will find in this section of the Platform:

  • Auto-Correction will spell correct the words in the user input to the closest matching word from the VA’s Knowledge Graph domain dictionary. Knowledge Graph domain dictionary comprises the words extracted from Knowledge Graph’s questions, alternate questions, nodes, and synonyms.
  • Bot Synonyms will enable the XO Platform to use the Bot Synonyms in Knowledge Graph as well. Inclusion of Bot Synonyms for intent detection by the KG engine requires training. Click Proceed when prompted to enable this setting and initiate training.
  • Lemmatization using Parts of Speech will enable the use of parts of speech associated with the words in the utterance to lemmatize.
  • Path Coverage can be used to define the minimum percentage of terms in the user’s utterance to be present in a path to qualify it for further scoring. The default setting is 50% i.e. at least half of the terms in the user utterance should match the node names and terms.
  • Minimum and Definitive Level for Knowledge Graph Intent allows you to set the confidence levels for a Knowledge Graph intent. You can view and adjust the confidence level percentages for the graph in one of three ranges:
    • Definitive Range – Matches in this range (green area) are picked and any other probable matches are discarded, default set to 93-100%.
    • Probable Range – Matches in this range (dark gray area) are considered for rescoring and ranking, by default set to 80-93%
    • Low Confidence Range – If no other intents have matched, low confidence matches (orange area) are presented to end-user for intent confirmation, by default set to 60-80%
    • Not Matching an Intent – The light gray area represents the knowledge graph intent NLP interpreter confidence levels as too low to match the knowledge graph intent, default set to 60%.
  • KG Suggestions Count: Define the maximum number of KG/FAQ suggestions (up to 5) to be presented when a definite KG intent match is not available. Default set to 3.
  • Proximity of Suggested Matches: Define the maximum difference (up to 50%) to be allowed between top-scoring and immediate next suggested questions to consider them as equally important. Default set to 5%. This applies to the matches in the probable range.
  • Manage Long Responses when the response size exceeds channel-specific limitations. You can choose to truncate the response or display the full response with a read more link. Read More link is included at the end of the message. On selecting this link, the full response is opened as an answer in the browser. The URL to open the long response in a web browser is set by default by the Platform. But you can provide a custom URL, too.
  • Search in Answer for the qualifying FAQs.
  • Qualify Contextual Paths in the Knowledge Graph using the context tags available in the context. Enabling this option will ensure that the paths are shortlisted using terms or tags from the context. These tags can come from previous matched paths or intent or custom-defined tags.

The Platform also offers some advanced configurations. Refer here for more details.

 

Search in Answer

This feature enables identifying FAQs by searching the user input against the answer section, instead of only matching with questions. This is a fallback mechanism only i.e. search in the answer section will be done only if no FAQs are identified from questions.

Note: This feature is not supported in all languages, refer here for details.

 

When the Search in Answer flag is enabled, the Knowledge Graph engine considers the answer text for identifying the intents also.

Once this option is enabled, you can specify whether to Inform the end-user that the answer is a probable answer. If selected a Standard Message to the effect is displayed, which can be customized using the Manage Response link. Learn more.

There are three ways in which you can render the response:

  1. Show Complete Response: Full response is sent as the answer to the user.
  2. Show only the Relevant Paragraph: Only the relevant paragraph from which the question was identified is sent as the response.
  3. Show only the Relevant Paragraph with Read More link: Only the relevant paragraph from which the question was identified is sent as the response.
    An additional Read More link is included at the end of the message. On selecting this link, the full response is opened as an answer in the browser. The URL to open the long response in a web browser is set by default by the Platform. But you can provide a custom URL (see below for details).

Custom URL Configuration

By default, the URL to open the long response in the web browser is set by the Platform. You have an option to provide a custom URL for rendering the FAQ answers.

The Platform will call the provided URL with details of the relevant message template (template id) and other necessary information.

The following API gives the full information of the FAQ:

URL: https://{{host-name}}/api/1.1/public/users/{{userId}}/faqs/resolvedResponse/{{respId}}

Method: get

Headers: {auth : JWT}

Sample Response:

{
“response”: “You can contact our Branch officials wherein you have submitted your documents.If the documents are in order, the account will be opened within 2 working days.”,
“primaryQuestion”: “How to check the status of my account opening?”
}

Lemmatization

Lemmatization in linguistics is the process of grouping together the inflected forms of a word so they can be analyzed as a single item, identified by the word’s lemma, or dictionary form. Using Parts of Speech information from the user utterance in the process of lemmatization can improve identifying a more accurate FAQ.

Following are some examples of the phrases as recognized by the KG engine with and without using parts of speech:

USER UTTERANCE NOT USING POS USING POS
What is my outstanding booking invoice balance outstand

book

outstanding

booking

I am filing for a visa so that I can travel file filing
What happens if my luggage exceeds the maximum weight? ? , happen

exceed

happens

exceeds

 

Knowledge Graph Training

Training your Assistant is not restricted to the Machine Learning and Fundamental Meaning engines. You must also train the Knowledge Graph (KG) engine, too.

The Ontology-based Knowledge Graph turns static FAQ text into an intelligent, personalized conversational experience. It uses domain terms and relationships thus reducing the training needs. It also has the capability to enable the ontology weighted features whenever ML gets confused and to automate conversational dialog for resolving appropriate answers.

The Few-Shot Knowledge Graph leverages Kore.ai’s LLM and lets you add FAQs without building an ontology. Less training and maintenance are required since you do not need to configure the graph term-by-term. Learn more about Knowledge Graph Types.

The Knowledge Graph engine thus responds to users’ intents by identifying the appropriate questions within the Knowledge Graph, and then presenting the user with the appropriate response.

You can find the Knowledge Graph by selecting your desired VA, then going to Build > Conversation Skills > Knowledge Graph.

Training a Few-Shot Knowledge Graph

Few-Shot Knowledge Graphs do not require an ontology and do not perform path qualification. Instead, they identify intents using semantic similarity and pattern recognition. However, if you want to train the VA on a specific use case for which the appropriate FAQ is not identified, you can map FAQs to an ontology, similar to what you would do with an Ontology-based Graph.

The main difference concerning training is that in the Few-Shot KG, Terms don’t require some of the training configurations needed in an Ontology Graph.:

  1. Default Terms are not available. The only exception is when you switch from an Ontology Graph, in which case existing Default terms are stored as such until updated. Afterward, Default terms become Organizer terms and can be set as Mandatory.
  2. Organizer Terms do not support Path-Level and Knowledge Graph Synonyms. They support Intent Preconditions and Context Output. 
  3. Mandatory Terms support Traits, Path-Level and Knowledge Graph Synonyms, Intent Preconditions, and Context Output, just like in an Ontology-based Graph.

You can set all Thresholds and Configurations except Path Coverage and Lemmatization using Parts of Speech, Search in Answer, and Qualify Contextual Paths, which are not supported by Few-Shot Graphs. 

See the Knowledge Graph Types Comparison Table for a detailed list of supported features.

Also, see Training Configuration below for training setup details.

Knowledge Graph Engine Capabilities

The following are the overall capabilities of the Knowledge Graph Engine:

  • Ease of Training using Synonyms: Kore.ai’s Knowledge Graph has a provision to associate synonyms against a graph node. This helps capture the variation in a question. For example, flight can be used as a synonym for plane in an FAQ such as How can I buy a plane ticket?.
  • Better Coverage with Alternate Questions: The Knowledge Graph has a provision to add alternate questions. This helps us to capture the various ways a user might ask the same question. For example, in How do I change my flight? we can add an alternate question as Can I change my flight?.
  • Improved Accuracy: Ontology-driven question-answers reduce the possibility of false positives.
  • Weighing Phrases using Traits: Kore.ai’s Knowledge Graph engine includes a concept of traits for filtering out irrelevant suggestions. See here for further details.
  • Ability to Mark Term Importance: The Knowledge Graph has a provision to mark that an ontology term is important. For example, in the question, How to book a flight, the word flight is an important term. If the flight keyword is not present in the user utterance, then it makes little sense.
  • Ability to Group Relevant Nodes: As the graph grows in size, managing graph nodes can become a challenging task. Using the organizer node construct of the ontology engine, developers can group relevant child nodes under a parent node.

FAQ Detection Steps

Here are the steps that the Knowledge Graph Engine takes when detecting FAQs:

  • Step 1: Extract Nodes: The KG engine processes the user utterance to extract the term (ontology nodes) present in the graph. It also takes into consideration the synonyms, traits, and tags associated with the terms.
  • Step 2: Query Graph: The KG engine fetches all the paths that consist of the extracted nodes.
  • Step 3: Shortlist Paths: All the paths consisting of 50% or more matching terms with the user utterance are shortlisted for further processing.

    Note: Path coverage computation doesn’t consider the root node.
  • Step 4: Filter with Traits: If traits are defined in the Knowledge Graph, paths shortlisted in the above step are further filtered based on the confidence score of a classification algorithm in user utterance. 
  • Step 5: Send to Ranker: The KG engine then sends the shortlisted paths to the Ontology Ranker Program.
  • Step 6: Score based on Cosine Similarity: The Ontology Ranker makes use of user-defined synonyms, lemma forms of word, n-grams, stop words, to compute the cosine similarity between the user utterance and the shortlisted questions. Paths are ranked in non-increasing order of cosine similarity score.
  • Step 7: Qualify Matches: The Ontology Ranker then qualifies the paths as follows:
    • Paths with score >= upper_threshold are qualified as an answer (definitive match).
    • Paths with lower_threshold < score < upper_threshold are marked as suggestions (probable match).
    • Paths with a score < lower_threshold are ignored.

Training Guidelines

From the Knowledge Graph, follow these steps to build and train the corresponding Knowledge Graph:

  1. Identify terms by grouping the unique words in each FAQ question. Build a hierarchy based on all such unique words.
  2. Ensure that each node has not more than 25 questions.
  3. Associate traits with terms to enable filtering FAQs from multiple identified results.
  4. Define synonyms for each term/node in the hierarchy. Ensure that all the different ways to call the term are defined.
  5. Depending on the importance of each term in a path, mark them as either mandatory or regular.
  6. Define alternative questions for each FAQ to ensure better coverage.
  7. Manage context for accurate response.
  8. Use Stop Words to filter unwanted utterances.

Training Configuration

This article presupposes that you already know the basics of building your Knowledge Graph. If not, please read this article.

In order to configure the training of your Knowledge Graph for improved VA performance, we recommend that you go through as many of the following parameters as possible. These parameters involve:

  • Adjusting the Term Type to your VA’s needs when adding terms to your graph,
  • Setting tags for FAQs to improve detection,
  • Configuring synonyms for Knowledge Graph terms to enhance path detection and help the VA find the appropriate questions to answer by widening the spectrum of words that can be used to find a specific question,
  • Adding Traits to detect relevant information that improves intent or scenario detection.
  • Manage Context to help users complete tasks faster and create more natural, human-like back and forth conversations.
  • Add Stop Words which will be discarded from intent scoring, even when they are a node term. 

Moving forward, we will discuss these parameters in detail.

Term Type

Designate the terms and tags in the Knowledge Graph as Default, or Mandatory, or Organizer depending on their importance in qualifying matching paths: You can configure term types by accessing the term/node settings.

The available term types are: 

  • Default: Default terms do not have any particular considerations in shortlisting qualified paths.
  • Mandatory: When you mark a term as Mandatory, all paths associated with the term are shortlisted for ranking only if the user’s utterance includes the mandatory term or its synonyms.
  • Organizer: Term can be marked as being a part of the Knowledge Graph only for organizing questions (this option is available only for terms, not tags).

Tags

When you type a question in the Intent Name Add Question field, the Knowledge Graph suggests some tags that you can add to the graph based on the text. To include a suggested term to the path, select the tag from the drop-down list that appears when the cursor is in the Add Term field. You can also add custom tags by typing them in the add term field and hitting the Enter/Return key.

After you add a tag, it is visible below the question like a tag everywhere the question appears. Tags work exactly like terms but are not displayed in the Knowledge Graph to avoid clutter. 

Synonyms

You can add multiple synonyms for each term in your Knowledge Graph, making the path discoverable for varied user utterances. You can add synonyms for a term from the term’s  Settings window.

When you add a synonym for a term in the Knowledge Graph, you can add them as local (Path Level) or global (Knowledge Graph level) synonyms.

Local Synonyms apply to the term only in that particular path, whereas Global Synonyms apply to the term even if it appears on any other path in the hierarchy.

To add synonyms for a term, follow the below steps:

  1. On the top left of the VA’s Knowledge Graph, hover over the node/term for which you want to add synonyms.
  2. Click the gear icon to open the Settings window.
  3. To add synonyms,  do the following:
    1. To add local synonyms, type them in the box under Path Level Synonyms.

    2. To add Global synonyms, click Edit then Add under Knowledge Graph Synonyms and enter them.
      Note: Press Enter after typing each synonym in the Synonyms box. If you type multiple synonyms without pressing Enter after each synonym, all the synonyms are considered as a single entity, even if they are separated by spaces.


       

      Note: These Knowledge Graph Synonyms can also be accessed from the Manage Synonyms option under the more options icon on the top-right of the Knowledge Graph page.


       

    3. You can use Bot Synonyms in the identification of KG terms. This option can be enabled either from the Threshold and Configurations or from More Options > Manage Synonyms.

      Once enabled, the bot-level synonyms that match with KG terms (or tags) are automatically displayed under the Bot Synonyms heading in the Synonyms section and are used by the KG engine. The Bot Synonyms are used similar to that of KG graph level synonyms, for path qualification and for question matching. When a node matches both with a bot synonym and a bot concept, the bot concept takes priority.
    4. To add synonyms for a child node, enter them in the Synonyms box next to the Child Terms listed at the bottom of the settings window.


Traits

You can create traits with common user utterances and then add them to the relevant terms in your Knowledge Graph. To know more about Traits, click here.

Traits are common across the XO Platform. If you have created Traits from the Natural Language section they are available for use here as well.

To create a trait, follow the below steps:

  1. On the top-right of the Knowledge Graph window, click the more options icon and then select Manage Traits.

  2. On the Manage Traits window, click New Trait.
  3. In the Trait Type and Trait Name field, enter a relevant name for the trait. For example, Flight Fare.
  4. In the Utterances field, enter all the utterances that you want to include in the trait. Examples of the Issues trait: First Class, Premium Economy, Economy, etc.
  5. Click Save & Add Rule or Save & Exit.

After you create a trait, you can assign it to multiple nodes in the Knowledge Graph.

To add a trait to a node/term, follow the below steps:

  1. On the top-left of your Knowledge Graph, hover over the terms to which you want to add the trait.
  2. Click the gear icon to open the Settings window.

Select the name of a trait from the Trait drop-down list and click Save

Note: Adding a trait to a node doesn’t add it to other nodes with the same name. You must add traits to each relevant node separately.

Context

You can Manage Context for the terms and tags by setting:

  • Intent Precondition – the context that should be present as a qualifier for this node or tag
  • Context Output – the context that should be populated to signify the execution of this task

Post the release of v8.0 of the Platform, context can be enabled for Organizer nodes as well. Enabling the Manage Context option allows you to set the context precondition and context output mentioned above. Click here for more on Context Management.

Note: Enabling the Manage Context option will not emit the term/node name by default.

 

Stop Words

Stop words present in the user utterance are discarded for scoring even if the stop word is used to define a node (or node synonyms).

The Knowledge Graph has a language-specific predefined set of stop words. This list can be customized to suit your requirements.

To edit the stop words list, follow the below steps:

  1. From the Knowledge Graph page, click on the more options icon and select Manage Stop Words.
  2. From the Manage Stop Words window, delete or add stop words.

Training Process

After you complete creating/editing the Knowledge Graph, click the Train button on the top-right of the Knowledge Graph window. When you perform this action, all the paths, synonyms, and question-answer sets are sent to the Graph DB engine.

Note: After every change that you make to the Knowledge Graph such as adding synonyms to a term or editing the name of a term, you must click the Train button for the changes to reflect in the bot responses.

 

The training fails if any single node has more than 100 questions. This limit was introduced in v7.3 to make the Knowledge Graph more efficient by improving the response times. In such failure cases, you can Download Errors CSV file which lists the path with more than 100 questions. You can use this file to rectify your Knowledge Graph.

Testing

When you complete creating the Knowledge Graph and training it, we recommend that you interact with the assistant and ask questions connected to the Knowledge Graph. Test the responses by using a variety of utterances so that you can identify missing terms, questions, alternative questions, synonyms, and traits. Learn more about utterance testing.

Thresholds & Configurations

To train and improve the performance, Thresholds and Configurations can be specified for all three NLP engines – FM, KG, and ML. You can access these settings from Natural Language > Training > Thresholds & Configurations.

Note: If your VA is multilingual, you can set the Thresholds differently for different languages. If not set, the Default Settings will be used for all languages. This feature is available from v7.0 onwards.

 

The settings for the Knowledge Graph engine are discussed in detail in the following sections.

Explore Thresholds and Configurations

To navigate to Thresholds and Configuration, please follow the steps below: 

  1. Open the VA for which you want to configure Knowledge Graph settings.
  2. Hover over the left pane and click Natural Language > Training.
  3. Click the Thresholds & Configurations tab.
  4. Below is a detailed discussion about the Knowledge Graph section on this page.

Here are the features that you will find in this section of the Platform:

  • Auto-Correction will spell correct the words in the user input to the closest matching word from the VA’s Knowledge Graph domain dictionary. Knowledge Graph domain dictionary comprises the words extracted from Knowledge Graph’s questions, alternate questions, nodes, and synonyms.
  • Bot Synonyms will enable the XO Platform to use the Bot Synonyms in Knowledge Graph as well. Inclusion of Bot Synonyms for intent detection by the KG engine requires training. Click Proceed when prompted to enable this setting and initiate training.
  • Lemmatization using Parts of Speech will enable the use of parts of speech associated with the words in the utterance to lemmatize.
  • Path Coverage can be used to define the minimum percentage of terms in the user’s utterance to be present in a path to qualify it for further scoring. The default setting is 50% i.e. at least half of the terms in the user utterance should match the node names and terms.
  • Minimum and Definitive Level for Knowledge Graph Intent allows you to set the confidence levels for a Knowledge Graph intent. You can view and adjust the confidence level percentages for the graph in one of three ranges:
    • Definitive Range – Matches in this range (green area) are picked and any other probable matches are discarded, default set to 93-100%.
    • Probable Range – Matches in this range (dark gray area) are considered for rescoring and ranking, by default set to 80-93%
    • Low Confidence Range – If no other intents have matched, low confidence matches (orange area) are presented to end-user for intent confirmation, by default set to 60-80%
    • Not Matching an Intent – The light gray area represents the knowledge graph intent NLP interpreter confidence levels as too low to match the knowledge graph intent, default set to 60%.
  • KG Suggestions Count: Define the maximum number of KG/FAQ suggestions (up to 5) to be presented when a definite KG intent match is not available. Default set to 3.
  • Proximity of Suggested Matches: Define the maximum difference (up to 50%) to be allowed between top-scoring and immediate next suggested questions to consider them as equally important. Default set to 5%. This applies to the matches in the probable range.
  • Manage Long Responses when the response size exceeds channel-specific limitations. You can choose to truncate the response or display the full response with a read more link. Read More link is included at the end of the message. On selecting this link, the full response is opened as an answer in the browser. The URL to open the long response in a web browser is set by default by the Platform. But you can provide a custom URL, too.
  • Search in Answer for the qualifying FAQs.
  • Qualify Contextual Paths in the Knowledge Graph using the context tags available in the context. Enabling this option will ensure that the paths are shortlisted using terms or tags from the context. These tags can come from previous matched paths or intent or custom-defined tags.

The Platform also offers some advanced configurations. Refer here for more details.

 

Search in Answer

This feature enables identifying FAQs by searching the user input against the answer section, instead of only matching with questions. This is a fallback mechanism only i.e. search in the answer section will be done only if no FAQs are identified from questions.

Note: This feature is not supported in all languages, refer here for details.

 

When the Search in Answer flag is enabled, the Knowledge Graph engine considers the answer text for identifying the intents also.

Once this option is enabled, you can specify whether to Inform the end-user that the answer is a probable answer. If selected a Standard Message to the effect is displayed, which can be customized using the Manage Response link. Learn more.

There are three ways in which you can render the response:

  1. Show Complete Response: Full response is sent as the answer to the user.
  2. Show only the Relevant Paragraph: Only the relevant paragraph from which the question was identified is sent as the response.
  3. Show only the Relevant Paragraph with Read More link: Only the relevant paragraph from which the question was identified is sent as the response.
    An additional Read More link is included at the end of the message. On selecting this link, the full response is opened as an answer in the browser. The URL to open the long response in a web browser is set by default by the Platform. But you can provide a custom URL (see below for details).

Custom URL Configuration

By default, the URL to open the long response in the web browser is set by the Platform. You have an option to provide a custom URL for rendering the FAQ answers.

The Platform will call the provided URL with details of the relevant message template (template id) and other necessary information.

The following API gives the full information of the FAQ:

URL: https://{{host-name}}/api/1.1/public/users/{{userId}}/faqs/resolvedResponse/{{respId}}

Method: get

Headers: {auth : JWT}

Sample Response:

{
“response”: “You can contact our Branch officials wherein you have submitted your documents.If the documents are in order, the account will be opened within 2 working days.”,
“primaryQuestion”: “How to check the status of my account opening?”
}

Lemmatization

Lemmatization in linguistics is the process of grouping together the inflected forms of a word so they can be analyzed as a single item, identified by the word’s lemma, or dictionary form. Using Parts of Speech information from the user utterance in the process of lemmatization can improve identifying a more accurate FAQ.

Following are some examples of the phrases as recognized by the KG engine with and without using parts of speech:

USER UTTERANCE NOT USING POS USING POS
What is my outstanding booking invoice balance outstand

book

outstanding

booking

I am filing for a visa so that I can travel file filing
What happens if my luggage exceeds the maximum weight? ? , happen

exceed

happens

exceeds

 

Menu