arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.25975cs.LGcs.AIcs.CL
收藏

神经是否梦想着原始运算?基于觉醒-睡眠压缩的Schank事件语义重新发现

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

Peter Balogh

AI总结:

本文通过觉醒-睡眠压缩方法自动发现Schank的事件语义原始运算,验证了其在不同数据集上的有效性与泛化能力。

摘要:

我们证明神经确实如此。罗杰·沙恩的概念依赖理论提出所有人类事件可分解为原始运算——ATRANS(占有转移)、PTRANS(物理移动)、MTRANS(信息转移)等——这些运算是从语言直觉中手工编码的。我们问:能否仅通过压缩压力自动发现这些原始运算?我们采用DreamCoder的觉醒-睡眠库学习方法来学习事件状态转换。给定事件作为前后世界状态对,系统搜索解释每个事件的运算组合(觉醒),然后在最小描述长度(睡眠)下提取重复模式作为库条目。从四个通用原始运算开始,系统发现了映射到Schank核心的运算:MOVE_PROP_has = ATRANS,CHANGE_location = PTRANS,SET_knows = MTRANS,SET_consumed = INGEST,以及复合运算(如“邮件”= ATRANS与PTRANS的组合)和不在Schank分类法中的新情感状态运算。我们在合成事件、ATOMIC(Sap等,2019)和GLUCOSE(Mostafazadeh等,2020)上进行了验证。在合成数据上,发现的库在100%覆盖下达到MDL,仅比Schank的手工编码运算高4%(相比Schank的81%)。在ATOMIC上,Schank仅覆盖10%;在GLUCOSE上,31%。发现的库覆盖了100%的两者,主要由心理/情感运算组成——CHANGE_wants(20%)、CHANGE_feels(18%)、CHANGE_is(18%)——这些在Schank的原始分类法中均无。从一个语料库发现的库在转移到另一个时,尽管有不同的注释方案和领域,降解仅在1位/事件以内,表明这些运算是由信息论决定的结构,而非数据集的偶然性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑