MBT2: a method for combining fragments of examples in example-based translation
Artificial Intelligence - Special issue: AI research in Japan
Learning translation templates from examples
Information Systems - Special issue on selected papers from 6th annual workshop on information technologies and systems, December 1996, Cleveland, Ohio, USA
Improving statistical natural language translation with categories and rules
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Learning translation templates from bilingual text
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Example-Based Machine Translation in the Pangloss system
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
WSEAS Transactions on Computers
Hi-index | 0.00 |
Recent years have witnessed rapid developments in the field of machine-translation, which has covered a wide range in research field and thus has been one of the researchers' major concerns in terms of translation exactness and costs. This paper presents a Super-Function based model which is aimed at constructing a translation system through the combination of translation principles. According to this model, translation cost is expected to be reduced and the quality of the translation to be greatly improved. In the present research, sufficient Chinese-Japanese causative sentence patterns have been employed as a language-database for experiment, which proves the suggested model can effectively improve translation quality within the range under discussion. Some problems concerning translation output have proven to be reduced, among which are the unnaturalness, the lack of logic and the mixture of varied mistakes. Meanwhile some methodological problems related to the present research are also included in the discussion for further improvement.