Do Neurons Dream of Primitive Operators? Wake-Sleep Compression Rediscovers Schank's Event Semantics

Abstract

We show that they do. Schank's conceptual dependency theory proposed that all events decompose into primitive operations -- ATRANS, PTRANS, MTRANS, and others -- hand-coded from linguistic intuition. Can the same primitives be discovered automatically through compression pressure alone? We adapt DreamCoder's wake-sleep library learning to event state transformations. Given events as before/after world state pairs, our system finds operator compositions explaining each event (wake), then extracts recurring patterns as new operators optimized under Minimum Description Length (sleep). Starting from four generic primitives, it discovers operators mapping directly to Schank's: MOVE_PROP_has = ATRANS, CHANGE_location = PTRANS, SET_knows = MTRANS, SET_consumed = INGEST, plus compound operators ("mail" = ATRANS + PTRANS) and novel emotional state operators absent from Schank's taxonomy. We validate on synthetic events and real-world commonsense data from the ATOMIC knowledge graph. On synthetic data, discovered operators achieve Bayesian MDL within 4% of Schank's hand-coded primitives while explaining 100% of events vs. Schank's 81%. On ATOMIC, results are more dramatic: Schank's primitives explain only 10% of naturalistic events, while the discovered library explains 100%. Dominant operators are not physical-action primitives but mental and emotional state changes -- CHANGE_wants (20%), CHANGE_feels (18%), CHANGE_is (18%) -- none in Schank's original taxonomy. These results provide the first empirical evidence that event primitives can be derived from compression pressure, that Schank's core primitives are information-theoretically justified, and that the complete inventory is substantially richer than proposed -- with mental/emotional operators dominating in naturalistic data.

Figures (4)

• Figure 1: Analogy between BPE tokenization and operator discovery. BPE merges frequent character pairs into new tokens; our sleep phase specializes operators by relation and composes frequent operator pairs---the same compression principle applied to typed state transformations.
• Figure 2: Example event decomposition. "John mailed Mary the book" is decomposed into ATRANS (possession transfer) composed with PTRANS (physical movement). The system discovers this decomposition from state diffs alone, without any linguistic knowledge.
• Figure 3: MDL learning curve across wake-sleep iterations. The core operators (ATRANS, PTRANS, MTRANS) emerge in iteration 1. Pruning removes 10 unused operators, further reducing MDL.
• Figure 4: Operator usage distribution in synthetic vs. ATOMIC data. Left: Synthetic data favors Schank's physical-action primitives (MTRANS, PTRANS, ATRANS). Right: ATOMIC data is dominated by mental/emotional operators (red) not in Schank's taxonomy, with physical-action operators (blue) accounting for $<$10% of usage.