Identifying Word Translations in Non-Parallel Texts
cmp-lg
2008-02-03 v1 Computation and Language
Abstract
Common algorithms for sentence and word-alignment allow the automatic identification of word translations from parallel texts. This study suggests that the identification of word translations should also be possible with non-parallel and even unrelated texts. The method proposed is based on the assumption that there is a correlation between the patterns of word co-occurrences in texts of different languages.
Cite
@article{arxiv.cmp-lg/9505037,
title = {Identifying Word Translations in Non-Parallel Texts},
author = {Reinhard Rapp},
journal= {arXiv preprint arXiv:cmp-lg/9505037},
year = {2008}
}
Comments
3 pages, requires aclap.sty and epic.sty