Skip to content

4. Conceptual Flow: Meaning → Text

SemantiK Architect is generation-first: it does not “interpret” text. It takes an unambiguous meaning payload and renders it into surface language.

Flow (at a glance)

Meaning (Frame or Ninai) → Normalize meaning → Apply discourse context (optional) → Pick language strategy (tier) → Realize text (lexicon + grammar) → Export (text, optionally UD) → Quality checks (optional)

Step-by-step

  1. Provide meaning (input)
    SemantiK Architect accepts meaning in two shapes:
  2. a strict, flat semantic frame (stable production input)

  3. a recursive Ninai-style object tree (more expressive, experimental input)

  4. Normalize meaning (adapter stage)
    Inputs are normalized into an internal “intent” representation:

  5. validate required fields / structure
  6. resolve defaults and normalize naming

  7. if the input is Ninai-style, an adapter walks the object tree and converts it into the internal intent/frame representation (a recursive object-walker approach, not text parsing)

  8. Use context for multi-sentence coherence (optional but important for naturalness)
    If a session is active, the system can track what entity is “in focus” and apply simple discourse decisions (e.g., reducing repeated names via pronouns when appropriate).

  9. Select a language strategy (coverage vs precision)
    To cover both high-resource and long-tail languages, the renderer selects a tiered strategy:

  10. a higher-precision rule-based path (when strong grammar resources exist)
  11. a broader-coverage factory/topology-based fallback (when they don’t)

  12. optional manual overrides can take precedence when available

  13. Realize the sentence (meaning → surface text)
    Rendering is the assembly step that combines:

  14. lexical choice (words and their properties)

  15. grammar / linearization (how those words become a correct sentence in the target language)

  16. Export (outputs)
    The primary output is natural language text. Optionally, the system can also output a Universal Dependencies (CoNLL-U) view for validation and evaluation.

  17. Close the loop with quality checks (optional workflow)
    A QA loop can compare generated output against a gold standard and flag regressions (including automated reporting workflows), so improvements remain stable over time.