Hitoshi Iida

Learn More
This paper proposes Example-Based Machine Translation (EBMT). EBMT retrieves similar examples (pairs of source texts and their translations) from the database, adapting the examples to translate a new source text. This paper compares the various costs of EBMT and conventional Rule-Based Machine Translation (RBMT). It explains EBMT's new features which RBMT(More)
It is important to correct the errors in the results of speech recognition to increase the performance of a speech translation system. This paper proposes a method for correcting errors using the statistical features of character co-occurrence, and evaluates the method. The proposed method comprises two successive correcting processes. The first process(More)
We have built a new speech translation system called ATR-MATRIX (ATR's Multilingual Automatic Translation System for Information Exchange). This system can recognize natural Japanese utterances such as those used in daily life, translate them into English and output synthesized speech. This system is running on a workstation or a high-end PC and achieves(More)
Transfer-Driven Machine Translation (TDMT) is presented as a method which drives the translation processes according to the nature of the input. In TDMT, transfer knowledge is the central knowledge of translation, and various kinds aml levels of knowledge are cooperatively applied to input sentences. TDMT effectively utilizes an example-based framework for(More)
This paper describes a practical method of automatic simultaneous interpretation utilizing an example-based incremental transfer mechanism. We primarily show how incremental translation is achieved in the context of an example-based framework. We then examine the type of translation examples required for a simultaneous interpretation to create naturally(More)