Jump to ContentJump to Main Navigation
Show Summary Details
More options …

STUF - Language Typology and Universals

Sprachtypologie und Universalienforschung

Editor-in-Chief: Stolz, Thomas

4 Issues per year

CiteScore 2017: 0.19

SCImago Journal Rank (SJR) 2017: 0.166
Source Normalized Impact per Paper (SNIP) 2017: 0.506

See all formats and pricing
More options …
Volume 60, Issue 2


Using Strong's Numbers in the Bible to test an automatic alignment of parallel texts

Michael Cysouw / Chris Biemann / Matthias Ongyerth
Published Online: 2009-09-25 | DOI: https://doi.org/10.1524/stuf.2007.60.2.158

We describe a method for the automatic alignment of parallel texts using co-occurrence statistics. The assumption of this approach is that words which are often found together are linked in some way. We employ this assumption to automatically suggest links between words in different languages, using Bible verses as information units. The result is a word-by-word alignment between different translations of the Bible. The accuracy of our method is evaluated by using Strong's numbers as a benchmark. Overall, the performance is high, indicating that this approach can be used to give an approximate gloss of Bible verses.

Keywords: parallel text; automatic word alignment; automatic glossing; statistical dictionary acquisition; co-occurrences

About the article

Published Online: 2009-09-25

Published in Print: 2007-07-01

Citation Information: STUF - Sprachtypologie und Universalienforschung, Volume 60, Issue 2, Pages 158–171, ISSN (Print) 0942-2919, DOI: https://doi.org/10.1524/stuf.2007.60.2.158.

Export Citation

Comments (0)

Please log in or register to comment.
Log in