Autor:	Kazem Taghva, Jeffrey Coombs, Ray Pereda, Thomas A. Nartker
Rok vydání:	2005
Předmět:	Information extraction Computer science Speech recognition Maximum-entropy Markov model ComputingMethodologies_DOCUMENTANDTEXTPROCESSING Optical character recognition computer.software_genre Precision and recall Hidden Markov model computer Task (project management)
Zdroj:	DRR
ISSN:	0277-786X
DOI:	10.1117/12.587799
Popis:	This paper presents the implementation and evaluation of a Hidden Markov Model to extract addresses from OCR text. Although Hidden Markov Models discover addresses with high precision and recall, this type of Information Extraction task seems to be affected negatively by the presence of OCR text.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::47595143522e6ca288fa5f461045da81 https://doi.org/10.1117/12.587799 Zobrazit plný text záznamu