A Matching Technique in Example-Based Machine Translation
cmp-lg
2008-02-03 v1 Computation and Language
Abstract
This paper addresses an important problem in Example-Based Machine Translation (EBMT), namely how to measure similarity between a sentence fragment and a set of stored examples. A new method is proposed that measures similarity according to both surface structure and content. A second contribution is the use of clustering to make retrieval of the best matching example from the database more efficient. Results on a large number of test cases from the CELEX database are presented.
Cite
@article{arxiv.cmp-lg/9508005,
title = {A Matching Technique in Example-Based Machine Translation},
author = {Lambros Cranias and Harris Papageorgiou and Stelios Piperidis},
journal= {arXiv preprint arXiv:cmp-lg/9508005},
year = {2008}
}
Comments
5 pages,LaTeX uses aclap.sty