Back to NLP Topics Best practices for intent naming, ML training, patterns, synonyms, and concepts. Follow these guidelines before building or training your assistant.
Intent Naming Do:
Use 2–4 words: action verb + object + optional modifier. Example: Send Detailed Report, Get 3 Day Forecast.
Use the same verb across similar tasks: Show Issue / Show Report, not Show Issue / Get Report.
Use numerical form for digits: Get 3 Day Forecast.
Don’t:
Use single-word actions.
Use determiners (the, a, my, that) or pronouns.
Use platform terms: task, alert, action, cancel, discard, amend, webhook.
Use entity values in intent names (e.g., avoid “Get Weather Today” where “Today” is an entity).
Use special characters: () & / \ $ [ ] + *
Use punctuation: – , . ! ? ' "
Use the app name or task type as part of the intent name.
Use the same word as both verb and noun across tasks (e.g., Update Issue / Get Updates).
Dialog Tasks: Map to verb + object — “the goal is to Do Something.”Alerts: Map to object only (no verbs) — “alert me on: Status Updates.”ML Training General:
Use batch test suites to compare ML models — there’s no fixed best configuration; iterate and compare.
Prepare utterances that are as diverse as possible.
Avoid noise (pleasantries); if unavoidable, spread it evenly across intents.
For large datasets, stop words and synonyms are auto-recognized by ML — explicit configuration is not required.
Using the Confusion Matrix:
Reassign utterances in False quadrants to the correct intent.
Improve cohesion by rephrasing or adding synonyms.
Avoid phrases that are similar across different intents.
Using K-fold Validation:
Ideal for large datasets (minimum 250 utterances total, 5 per intent).
Track Precision, Recall, and F1. Prioritize a higher Recall score.
Patterns Patterns match idiomatic or non-obvious expressions that synonyms can’t cover. Pattern matches take priority over synonym matches.
General rules:
Use at minimum 3 words.
Use canonical forms: infinitive verbs, singular nouns.
Use lowercase; use US spelling.
Avoid determiners, pronouns, digits.
Don’t use elision (what's), special characters, or punctuation.
Pattern Operators Operator Syntax Description AND (ordered) (X Y)Words must appear in sequence. Default. Allows up to 3 wildcards between words. OR [X Y Z]Any of the listed words can appear. NOT !XWord must not appear. Applies “not after this point.” Optional {X}Word is optional. Enforce phrase X_YWords must appear together with no words in between. Concept ~conceptMatches any member of the concept group. Unordered <<X Y>>Words can appear in any order. Start of statement <Match must begin at the start of the input. End of statement >Match must end at the end of the input. Quote 'word'Matches the exact word; disables canonical form matching.
Entity Patterns
Include the positional wildcard * to mark where the entity appears.
Use surrounding words to delimit the entity search range.
Use < and > to mark sentence boundaries.
Don’t use field names or their synonyms in entity patterns.
Only the first instance with a valid value is extracted.
Example — Extracting ToFlight and FromFlight:
ToFlight pattern: to *1FromFlight pattern: from * to and to from *1
Negative Patterns Negative patterns prevent false intent matches.
Example: was trying to * — prevents triggering Book a Flight when the user says “I was trying to book a flight when I faced an issue.”To enable: Natural Language > NLU Config > Ranking and Resolver Engine > Negative Patterns .
Synonyms Use synonyms when the same concept can be expressed with different words. Synonyms are unidirectional (tool=bar ≠ bar=tool).
Do:
Use canonical forms (infinitive verbs, singular nouns).
Use lowercase and US spelling.
Keep phrases under 5 words.
Use intent-driven synonyms: get is a synonym for show if the action means “find and display.”
Don’t:
Add synonyms to determiners, pronouns, or digits.
Use a synonym that could match conflicting tasks.
Use special characters or punctuation.
Assign synonyms to multiple words in a single entry.
Abbreviate to fewer than 2 letters.
Synonym Match Types Type Behavior Partial Match (default)One or more words in the input match one or more synonym words. Exact Match Input must contain all words in the synonym. Enclose synonym in "double quotes". Full Match Entire input must match the synonym. Enclose in <angular brackets>. Canonical Form Match (default)Matches the synonym or its canonical form. Prefix with ' to disable.
Synonyms apply to both intent and entity identification. Entity identification is triggered only after an intent is matched.
Concepts Concepts group related terms under a single label, usable in patterns.
Naming rules:
Must start with ~.
Allowed characters: a–z, A–Z, 0–9, _.
At least one letter after ~.
Cannot start or end with _.
Case-insensitive.
Valid: ~my_concept, ~Sample, ~test123
Invalid: ~_concept, ~concept_, ~a-concept, ~123testUse concepts in patterns: buy ~fruit matches buy orange, buy banana, etc.
System concepts: Pre-built by the platform (e.g., ~emohello, ~yes, ~no). Add the ~disable_help concept to disable the default help response.Standard Responses Standard responses are template messages for common conversational situations: ambiguity resolution, authorization requests, confirmations, interruptions.
Customize them at Natural Language > Standard Responses . Responses support:
Plain text or JavaScript for dynamic content.
Contextual tags replaced at runtime (e.g., <list-of-tasks>).
Channel-specific formatting.
Knowledge Graph — Key Considerations The KG model adds domain intelligence on top of ML and FM. Assign FAQs to nodes based on key domain terms to improve disambiguation.
Traits in KG: Use when FAQs are mutually exclusive in nature. For example, “booking process” vs. “booking issues” — creating separate traits ensures the engine doesn’t suggest booking process FAQs for issue-related queries.Use traits judiciously — overuse causes false negatives. Ensure:
Good trait coverage across utterances.
Traits are mutually exclusive where intended.
All relevant FAQs are tagged to the correct trait.
