用压缩原理自动发现人类事件的原始操作，效果超过人工设计。
Do Neurons Dream of Primitive Operators? Wake-Sleep Compression Rediscovers Schank's Event Semantics
- 通过最小描述长度原则，从事件前后状态中自动提取通用操作符。
- 在合成数据上覆盖率达100%，比人工设计的体系高出近20个百分点。
- 发现大量情感心理类操作符，适用于认知建模与通用智能研究。
我们证明了神经元会做梦。罗杰·沙克提出的概念依赖理论认为，所有人类事件可分解为基本操作——如转移占有（ATRANS）、物理移动（PTRANS）、信息传递（MTRANS）等，这些由语言直觉手工设计。本文提出：仅靠压缩压力，能否自动发现相同的原始操作？我们改编了DreamCoder的唤醒-睡眠库学习机制，将事件视为前后世界状态对，系统在唤醒阶段搜索解释每个事件的操作组合，在睡眠阶段基于最小描述长度提取重复模式作为库条目。初始使用四个通用操作符，最终发现了对应沙克核心操作的映射：MOVE_PROP_has = ATRANS，CHANGE_location = PTRANS，SET_knows = MTRANS，SET_consumed = INGEST，还发现复合操作（如“邮寄”= ATRANS + PTRANS）及沙克未包含的新情感状态操作符。在合成数据、ATOMIC（Sap et al., 2019）和GLUCOSE（Mostafazadeh et al., 2020）上验证：合成数据上，新库的MDL仅比沙克体系高4%，覆盖率达100%（沙克为81%）；在ATOMIC上，沙克仅覆盖10%，新库达100%；在GLUCOSE上，沙克31%，新库100%。新库主导为心理/情绪操作符：CHANGE_wants（20%）、CHANGE_feels（18%）、CHANGE_is（18%），均不在原体系中。不同语料库间库迁移仅损失不到1比特/事件，表明这些操作符是信息论决定的结构，而非数据集偏差。
原文摘要 · Abstract (English)
We show that they do. Roger Schank's conceptual dependency theory proposed that all human events decompose into primitive operations -- ATRANS (transfer of possession), PTRANS (physical movement), MTRANS (information transfer), and others -- hand-coded from linguistic intuition. We ask: 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, the system searches for operator compositions explaining each event (wake), then extracts recurring patterns as library entries under Minimum Description Length (sleep). Starting from four generic primitives, it discovers operators mapping to Schank's core: MOVE_PROP_has = ATRANS, CHANGE_location = PTRANS, SET_knows = MTRANS, SET_consumed = INGEST, plus compound operators (e.g., "mail" = ATRANS composed with PTRANS) and novel emotional-state operators absent from Schank's taxonomy. We validate on synthetic events, ATOMIC (Sap et al., 2019), and GLUCOSE (Mostafazadeh et al., 2020). On synthetic data, the discovered library achieves MDL within 4% of Schank's hand-coded primitives at 100% coverage (vs. Schank's 81%). On ATOMIC, Schank covers only 10%; on GLUCOSE, 31%. The discovered library covers 100% of both, dominated by mental/emotional operators -- CHANGE_wants (20%), CHANGE_feels (18%), CHANGE_is (18%) -- none in Schank's original taxonomy. Libraries discovered from one corpus transfer to the other with under 1 bit/event degradation despite different annotation schemes and domains, suggesting the operators are information-theoretically determined structure, not dataset artifacts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。