A language goes extinct when people no longer try to speak it or learn it, or it can also go extinct when all of the population who speak the language become deceased and are left with no other surviving members that could preserve it. Linguists can help preserve a language by saving traces of the language through written materials, videos, audios, and teaching classes on it. Some dead language can be brought back to life, if there are enough resources available to but a lot are not. Currently, some efforts are underway to document linguistic diversity involving AI. There have been many cases of people trying to use AI to reduce the challenges of documenting rare languages, creating online dictionaries, digital archives, and media collections. One example is that a group of Dartmouth students built an AI-driven framework called NüshuRescue that can potentially be adapted to other “low-resource” languages, which have fewer written or translated materials available for training AI systems. The tool used minimal data, 35 pairs of matching sentences in Chinese and Nüshu (a language rooted in Hunan province, meaning “women’s writing”) to train a large language model that had no prior knowledge of Nüshu to expand the database of text in the script through translations from Chinese.
You need to be a member of The SDLAP Ning to add comments!
Replies