arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.02416cs.FL
收藏

超图Lambek文法的表达能力

Expressive Power of Hypergraph Lambek Grammars

Tikhon Pshenitsyn

AI总结:

本文证明了超图Lambek文法与带推导长度线性限制的双推出超图文法生成相同语言类,完整刻画了其表达能力,并推论其包含上下文超边替换文法。

摘要:

超图Lambek文法(HL-grammars)是一种基于超图Lambek演算生成图语言的新型逻辑方法。在本文中,我们建立了HL-文法与基于双推出(DPO)方法的超图文法之间的精确关系:我们证明了HL-文法生成的语言类与具有推导长度线性限制的DPO文法生成的语言类相同。这可以看作是对HL-文法表达能力的完整刻画,同时也可视为Pentus定理的一个类比,该定理指出Lambek文法生成的语言类与上下文无关文法相同。作为一个推论,我们证明了HL-文法包含上下文超边替换文法。

英文摘要:

Hypergraph Lambek grammars (HL-grammars) is a novel logical approach to generating graph languages based on the hypergraph Lambek calculus. In this paper, we establish a precise relation between HL-grammars and hypergraph grammars based on the double pushout (DPO) approach: we prove that HL-grammars generate the same class of languages as DPO grammars with the linear restriction on lengths of derivations. This can be viewed as a complete description of the expressive power of HL-grammars and also as an analogue of the Pentus theorem, which states that Lambek grammars generate the same class of languages as context-free grammars. As a corollary, we prove that HL-grammars subsume contextual hyperedge replacement grammars.

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。

↑