Skip to main content
Back to NLP Topics The ML engine maps user utterances to intents using example-based training. It supports supervised and unsupervised learning, with a range of network types for different use cases.

​
How the ML Engine Works

Intent detection pipeline:
  1. User utterance is preprocessed (tokenization, stop word removal, lemmatization, n-grams).
  2. The ML model classifies the utterance as a probable or definitive match against trained intents.
  3. Results are passed to Ranking and Resolver.
Entity extraction: After intent is identified, the engine extracts entity values from the utterance using NER (Named Entity Recognition) trained annotations. Supervised vs. unsupervised learning:
  • Unsupervised (auto-expand): The assistant learns from all successful interactions automatically.
  • Supervised (recommended): Developers monitor interaction logs, tune NLP settings for failures, and retrain.

​
Add ML Utterances

  1. Go to Natural Language > Training > Intents.
  2. Select an intent and add sample utterances.
  3. Click Train to update the model.
Utterance guidelines:
  • Utterances do not need to be full sentences; phrases work too.
  • For distinct intents (e.g., “Find Flight” vs. “Book Hotel”): 200–300 utterances each.
  • For similar intents (e.g., “Change Seat” vs. “Change Flight”): 1000+ utterances each.
  • For Deep Neural Networks: larger datasets (data-hungry models) produce better results.

​
ML Network Types

Configure under Natural Language > NLU Config > Engine Tuning > ML.
Network TypeDescription
Standard (default)Bag-of-words classification. Suitable for most use cases.
MLP-BOWMulti-layer perceptron with bag-of-words features.
MLP-WordEmbeddingsMLP with pre-trained word embeddings.
LSTMRecurrent neural network. Captures sequential context.
CNNConvolutional neural network. Captures local n-gram patterns.
TransformerTransformer-based model. High accuracy for English.
KAENKore.ai custom model. Improved accuracy for English.
Zero-shot ModelNo training required; uses semantic similarity. Requires NLP V3.
Few-shot Model (Kore.ai Hosted Embeddings)LLM-based semantic similarity. Reduces training data requirements. Requires NLP V3.

​
Thresholds and Configuration

Go to Natural Language > NLU Config > Engine Tuning > Machine Learning.
SettingDescription
ML ThresholdMinimum confidence score for a probable match (default: 0.3).
Auto TrainingAutomatically retrain the model when utterances are added or modified.
Network TypeSelect the ML model architecture.
Stop WordsEnable/disable stop word removal during training.
Synonyms in MLInclude bot synonyms in ML training.

​
Synonyms and Concepts for ML

Bot Synonyms: Go to Training > Bot Synonyms. Add synonyms for words in task and entity names. Synonyms are app-wide.
  • To add: click New Synonym, enter the keyword and its synonyms (press Enter after each).
  • Parallel editing is supported — multiple users can add/delete synonyms concurrently without data conflicts.
Entity Synonyms: Go to Training > Entities. Add synonyms per entity node. Concepts: Custom concept groups prefixed with ~. Define in Training > Concepts. Used in patterns and entity detection.

​
App Substitutions

Define domain-specific word replacements using the ~bot_substitutions concept: 
Chevy|Chevrolet    → replaces "Chevy" with "Chevrolet"
?_km|kilometers    → replaces "5 km" with "5 kilometers"
Syntax: original_word|replacement (case-insensitive match, case-sensitive replacement).

​
App Word Aliases

Define alternate spellings or STT transcription corrections using Bot Synonyms with a + prefix. Example: +Alpha Romeo as an alias for Alfa Romeo — corrects speech-to-text transcription errors.
  • Aliases do not change the original utterance.
  • They normalize values returned for Custom Concept entities.

​
Homophones

Handle words that sound the same but have different spellings. Define using a concept with | separator: 
write|right|rite
The engine considers all homophones during POS tagging and replaces the word if a homophone is a better grammatical fit. To define: Training > Concepts > New Concept — enter homophones separated by |.

​
Emoji Support

Import default emoji mappings into system concepts to handle emoji inputs:
  1. Go to Natural Language > Training > Intents > ⋯ > Import Emojis into Concepts.
  2. Emojis are added to system concepts (e.g., ~emohappy, ~emohello).
  3. Review and remove unwanted emojis after import.

​
Patterns for Intents and Entities

See NLP Guidelines — Patterns for operators, syntax, and examples. Add intent pattern:
  1. Training > Intents → click Patterns / +Pattern for an intent.
  2. Enter patterns; press Enter between each.
Add entity pattern:
  1. Training > Entities → click the edit icon for an entity.
  2. Select the Patterns tab → enter patterns.
Add intent rules:
  1. Training > Intents → click Rules / +Rule for an intent.
  2. Enter Trait or context tag conditions using AND/OR operators.
Negative patterns:
  1. Enable at NLU Config > Ranking and Resolver Engine > Negative Patterns.
  2. Per intent: Training > Intents → select intent → Negative Patterns tab → add patterns.

​
NLU Config — FM Engine Tuning

SettingDescription
Intent Detection using Task Name WordsWhen disabled, intent is detected only if input starts/ends with the exact task name. Useful for tasks with shared words (e.g., multiple “order” tasks). Enabled by default.
FM ThresholdMax % above the top-scoring intent allowed for other intents to be considered (0–20%; default 2%). Supported for English, Spanish, French, German.