Flattened Syntactical Phrase-Based Translation Model for SMT

Autor:	Tianshun Yao, Qing Chen
Rok vydání:	2009
Předmět:	Structure (mathematical logic) Phrase Translation system Parsing Syntax (programming languages) Machine translation Computer science business.industry computer.software_genre Translation (geometry) Variable (computer science) Artificial intelligence business computer Natural language processing
Zdroj:	Computer Processing of Oriental Languages. Language Technology for the Knowledge-based Economy ISBN: 9783642008306 ICCPOL
DOI:	10.1007/978-3-642-00831-3_34
Popis:	This paper proposed a flattened syntactical phrase-based translation model for Statistical Machine Translation (SMT) learned from bilingual parallel parsed texts. The flattened syntactical phrases are sets of ordered leaf nodes with their father nodes of single syntax trees or forests ignoring the inner structure, containing lexicalized terminals and non-terminals as variable nodes. Constraints over the variable nodes in target side guarantee correct syntactical structures of translations in accordant to the syntactical knowledge learned from parallel texts. The experiments based on Chinese-to-English translation show us a predictable result that our model achieves 1.87% and 4.76% relative improvements, over Pharaoh, the state-of-art phrase-based translation system, and the system of traditional tree-to-tree model based on STSG.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a99c72d191939e8cb5307e94d8c316df https://doi.org/10.1007/978-3-642-00831-3_34 Zobrazit plný text záznamu