Autor:	DeGiuli, E.
Rok vydání:	2018
Předmět:	Condensed Matter - Disordered Systems and Neural Networks Computer Science - Computation and Language Computer Science - Formal Languages and Automata Theory
Zdroj:	Phys. Rev. Lett. 122, 128301 (2019)
Druh dokumentu:	Working Paper
DOI:	10.1103/PhysRevLett.122.128301
Popis:	Many complex generative systems use languages to create structured objects. We consider a model of random languages, defined by weighted context-free grammars. As the distribution of grammar weights broadens, a transition is found from a random phase, in which sentences are indistinguishable from noise, to an organized phase in which nontrivial information is carried. This marks the emergence of deep structure in the language, and can be understood by a competition between energy and entropy. Comment: 5 pages + 3 pages SI
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1809.01201 Zobrazit plný text záznamu View this record from Arxiv