Adaptable, Community-Controlled, Language Technologies for Language Maintenance.
Lori S. Levin · 2009
Endangered languages may require more flexible language technologies than stable ones because they may not be standard-ized and they may be in a cycle of losing, replacing, and borrowing vocabulary and grammar. This paper argues that the cov-erage and content of language technologies should be in the hands of the speech com-munity, and that it needs to be adaptable and learn from users. This calls for new ap-proaches, possibly based on active learning to allow the language technologies to be as flexible and changeable as languages gen-erally are. The paper also addresses ways in which the development of a machine translation system can be initiated when resources are scarce, including the expe-rience of the AVENUE project with Ma-pudungun (Chile) and Iñupiaq (Alaska). 1