在固定有限单调型下上下文无关语言的分布学习
Distributional Learning of Context-Free Languages under Fixed Finite-Semigroup Typing
AI总结:
本文研究在固定可识别同余关系下上下文无关语言的分布学习,提出有限类型重建理论,并证明在正样本下可精确重建,同时对线性子类给出多项式上界。
摘要:
我们研究在给定为显式有限单oid同态h:Σ*→M的核的固定可识别同余~_h下上下文无关语言的分布学习。对于固定-h设置,我们开发了上下文无关~_h-可替换语言的有限类型重建理论。从简化的上下文无关文法出发,我们引入了记录生成类型和外上下文类型的类型细化,证明相关结构集中于有限类型重建基中,并证明该基可通过有限观察集暴露。因此,相同非终端符号的出现可能必须在它们的外h-上下文不同的情况下被分离。我们随后证明从正样本中精确重建。从任何有限样本K⊆Σ*,我们构造一个规范假设文法\hat{G}(K),并证明一旦K包含与目标类型文法相关的有限观察集,\hat{G}(K)将生成目标语言。因此,对于每个显式有限单oid同态h,上下文无关~_h-可替换语言的类\mathcal{C}_h^{\mathrm{cf}}可在正样本下从极限可识别,具有多项式时间假设构造和更新。对于线性子类\mathcal{C}_h^{\mathrm{lin}},我们进一步证明特征样本大小和词长的多项式上界。因此,同一学习器对线性子类给出完整的多项式时间和数据结果。
英文摘要:
We study positive-data learning of context-free languages whose nonempty factors are typed by a fixed morphism $s:Σ^+\to S$ into a finite semigroup. A polynomial-time set-driven operator reconstructs each substitutable target from finite positive witnesses; a separate conservative learner identifies nonempty targets in Gold's sense. The encoded characteristic-data size is polynomial in grammar size and a typed shortest-yield parameter. Ordinary grammar thickness suffices when the typing is determined by a fixed prefix-suffix window and a finite-group value; for linear targets, linear grammar size alone suffices. Conversely, a fixed two-element semilattice typing yields finite targets with grammars of size and ordinary thickness both $O(n)$ that require exponentially long characteristic samples. The lower bound applies to any set-driven operator admitting characteristic samples for the fixed-typing class. Retyping closure, examples beyond fixed windows, and a Dyck-language obstruction delineate the framework's scope.
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。