When is an embedded MT system 'good enough' for filtering?

Autor:	Carol Van Ess-Dykema, Clare R. Voss
Rok vydání:	2000
Předmět:	Arabic business.industry Computer science computer.software_genre language.human_language Haitian Creole Ranking Text processing language Artificial intelligence Data mining business computer Natural language processing
Zdroj:	NAACL-ANLP 2000 Workshop on Embedded machine translation systems.
DOI:	10.3115/1117586.1117587
Popis:	This paper proposes an end-to-end process analysis template with replicable measures to evaluate the filtering performance of a Scan-OCR-MT system. Preliminary results across three language-specific FALCon systems show that, with one exception, the derived measures consistently yield the same performance ranking: Haitian Creole at the low end, Arabic in the middle, and Spanish at the high end.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02c2c27a87c417c8f52a5f49a0ba6a31 https://doi.org/10.3115/1117586.1117587 Zobrazit plný text záznamu