Self-Organizing Computational Efficiency in Quranic Grammar

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3AYJHNIM9R" target="_blank" >RIV/00216208:11320/22:YJHNIM9R - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-69288-9_8" target="_blank" >https://doi.org/10.1007/978-3-030-69288-9_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-69288-9_8" target="_blank" >10.1007/978-3-030-69288-9_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Self-Organizing Computational Efficiency in Quranic Grammar

Popis výsledku v původním jazyce

The existing knowledge-based and data-driven systems for Arabic morphological analysis are all suffering three main computational drawbacks, viz. efficiency, domain, and abstraction. Although the knowledge-based systems employ heavy lexical databases, they generate highly ambiguous tags. And to cover a new domain their lexicon should be costly modified. They also do not provide the linguistic abstraction preferred especially in computational linguistics. Similarly, the systems developed following a data-driven approach ignore the linguistic tractability for Arabic morphology and are highly dependent on big sizes of domain-specific training data. The source of these drawbacks may be traced in the morphological approach they employ in their knowledge base or in their training data. This chapter introduces regex morpho-syntax for Arabic, a highly efficient formalism originating from the basic grammatical rules developed for diacritizing the Quran fourteen centuries ago. The developed formalism is implemented in the knowledge base of Mobin morpho-syntactic parser and tagger. The achieved F-score of 0.967 for the computational effectiveness of the system as well as its significant comparative efficiency measured in terms of Kolmogorov complexity highlights the inherent computational efficiency in Quranic grammar.

Název v anglickém jazyce

Self-Organizing Computational Efficiency in Quranic Grammar

Popis výsledku anglicky

The existing knowledge-based and data-driven systems for Arabic morphological analysis are all suffering three main computational drawbacks, viz. efficiency, domain, and abstraction. Although the knowledge-based systems employ heavy lexical databases, they generate highly ambiguous tags. And to cover a new domain their lexicon should be costly modified. They also do not provide the linguistic abstraction preferred especially in computational linguistics. Similarly, the systems developed following a data-driven approach ignore the linguistic tractability for Arabic morphology and are highly dependent on big sizes of domain-specific training data. The source of these drawbacks may be traced in the morphological approach they employ in their knowledge base or in their training data. This chapter introduces regex morpho-syntax for Arabic, a highly efficient formalism originating from the basic grammatical rules developed for diacritizing the Quran fourteen centuries ago. The developed formalism is implemented in the knowledge base of Mobin morpho-syntactic parser and tagger. The achieved F-score of 0.967 for the computational effectiveness of the system as well as its significant comparative efficiency measured in terms of Kolmogorov complexity highlights the inherent computational efficiency in Quranic grammar.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Efficiency in Complex Systems

ISBN

978-3-030-69288-9

ISSN

—

e-ISSN

—

Počet stran výsledku

23

Strana od-do

129-151

Název nakladatele

Springer International Publishing

Místo vydání

—

Místo konání akce

Cham

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—