Web Tool for Automated Document Formatting Verification

Autor:	Andrei Berezhkov, Viacheslav Martsinkevich
Jazyk:	angličtina
Rok vydání:	2023
Předmět:	catboost parsing document formatting verification pdf odt docx service architecture machine learning nlp software architecture Telecommunication TK5101-6720
Zdroj:	Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 33, Iss 2, Pp 375-381 (2023)
Druh dokumentu:	article
ISSN:	2305-7254 2343-0737
DOI:	10.5281/zenodo.8005373
Popis:	The article discusses the algorithms for document compilation check in compliance with standards and regulatory documents. The paper presents various approaches and methods of extraction of structural elements and their properties from PDF, ODT, DOCX documents; reveals machine-learning opportunities in terms of class extraction and further structural elements classification. The machine-learning methods are also used to provide recommendations on possible errors. The article introduces automated document formatting verification service architecture.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/3e145407480c413488a8858ad6c429d9 Zobrazit plný text záznamu View record in DOAJ