Abstract

This paper describes an example-based machine translation (EBMT) system which relays on various knowledge resources. Morphologic analyses abstract the surface forms of the languages to be translated. A shallow syntactic rule formalism is used to percolate features in derivation trees. Translation examples serve the decomposition of the text to be translated and determine the transfer of lexical values into the target language. Translation templates determine the word order of the target language and the type of phrases (e.g. noun phrase, prepositional phase, ...) to be generated in the target language. An induction mechanism generalizes translation templates from translation examples. The paper outlines the basic idea underlying the EBMT system and investigates the possibilities and limits of the translation template induction process.

Citations

892	Mathematics of Statistical Machine Translation: Parameter Estimation - Brown, Pietra, et al. - 1993
502	A statistical approach to machine translation - Brown, Cocke, et al. - 1990
114	Toward Memory-Based Translation - Sato, Nagao - 1990
19	Linking translation memories with example-based machine translation - Carl, Hansen - 1999
19	MPRO - Ein System zur Analyse und Synthese deutscher Wörter - Maas - 1996
19	Example-Based Machine Translation Using Connectionist Matching - McLean - 1992
13	Example-Based Machine Translation: An Adaptation-Guided Retrieval Approach - Collins - 1998
11	Shallow Post Morphological Processing with KURD - Carl, Schmidt-Wigger - 1998
10	Applications in Multilingual Machine Translation - Sharp, Streiter - 1995
5	Integrating knowledge bases and statistics in MT - Knight, Chander, et al. - 1994
3	Adaptation-Guided retrieval: Approaching EBMT with caution - Collins, Cunningham - 1997
3	Corpus-Based Learning of Generalised Parse Tree Rules for Translation - Guvenir, Tunc - 1996