Paper: Automatic Detection of Cognates Using Orthographic Alignment

ACL ID P14-2017
Title Automatic Detection of Cognates Using Orthographic Alignment
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Words undergo various changes when en- tering new languages. Based on the as- sumption that these linguistic changes fol- low certain rules, we propose a method for automatically detecting pairs of cog- nates employing an orthographic align- ment method which proved relevant for se- quence alignment in computational biol- ogy. We use aligned subsequences as fea- tures for machine learning algorithms in order to infer rules for linguistic changes undergone by words when entering new languages and to discriminate between cognates and non-cognates. Given a list of known cognates, our approach does not require any other linguistic information. However, it can be customized to integrate historical information regarding language evolution.