Abstract
We use an iterative process of multi-gram alignment between associated words in different languages in an attempt to identify cognates. To maximise the amount of data, we use practical orthographies instead of consistently coded phonetic transcriptions. First results indicate that using practical orthographies can be useful, the more so when dealing with large amounts of data.
Cite
CITATION STYLE
Cysouw, M., & Jung, H. (2007). Cognate identification and alignment using practical orthographies. In Proceedings of 9th Meeting of the ACL Special Interest Group in Computational Morphology and Phonology, SIGMORPHON 2007 - Held in conjunction with the 45th Annual Meeting of the Association of Computational Linguistics, ACL 2007 (pp. 109–116). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1626516.1626530
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
