Empirical methods for exploiting parallel texts
Empirical methods for exploiting parallel texts
Bitext maps and alignment via pattern recognition
Computational Linguistics
A word-to-word model of translational equivalence
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
HLT '93 Proceedings of the workshop on Human Language Technology
DUSTer: A Method for Unraveling Cross-Language Divergences for Statistical Word-Level Alignment
AMTA '02 Proceedings of the 5th Conference of the Association for Machine Translation in the Americas on Machine Translation: From Research to Real Users
Hi-index | 0.00 |
This article reviews some recently invented methods for automatically extracting translation lexicons from parallel texts. The accuracy of these methods has been significantly improved by exploiting known properties of parallel texts and of particular language pairs. The state of the art has advanced to the point where non-compositional compounds can be automatically identified with high reliability, and their translations can be found. Most importantly, all of these methods can be smoothly integrated into the usual work flow of MT system developers. Semi-automatic MT lexicon construction is likely to be more efficient and more accurate than either fully automatic or fully manual methods alone.