An example-based method for transfer-driven machine translation

This paper presents a method called Transfer-Driven Machine Translation (TDMT), which utilizes an example-based framework for various process and combines multi-level knowledge. An example-based framework can achieve quick processing and consistently describe knowledge. It is useful for spoken-language translation, which needs robust and efficient translation. TDMT strengthens the example-based framework by integrating it with other frameworks. The feasibility of TDMT and the advantages of the example-based framework have been confirmed with a prototype system, which translates spoken dialog sentences from Japanese to English.