Abstract:This work addresses an important problem in Example-Based Machine Translation (EBMT), namely how to make retrieval of the example that best matches the input more efficient. The use of clustering is proposed, to enable the application of the same similarity metric to first limit the search space and then locate the best available match in a database. Evaluation results are presented on a large number of test cases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.