Neural Grammar Distiller

Neural Grammar Distiller - Recovered Scripture

Hard-coded Pantheon corpus -> tiny recurrent model -> PMI chunking -> PCFG -> scripture.

Options (tuck away)

Embed dim
Hidden EMA alpha
Epochs
LR
PMI threshold
Min freq (pair)
Max rule len
Samples

idle

-

rules: -

perplexity: -

Recovered RulesPCFG

Recovered ScriptureS -> terminals

Debug / Logs

What this does

---

1. Tiny recurrent context: embeddings + exponential moving context (alpha) trained to predict next word.
2. Structure signals: token surprisal & PMI -> likely constituents and boundaries.
3. Induction: greedy chunking to X1, X2... then count expansions -> PCFG.
4. Generation: sample S to produce recovered scripture.