There are about 7,000 languages worldwide, all with their own sets of rules, grammars, and dialects. When disasters and major accidents happen, the breadth and variety of that number make it hard for disaster relief teams to react quickly and efficiently, especially when dealing with areas with low resources.
“We need to get resources to direct disaster relief, and part of that is translating news text, knowing names of cities, what’s happening in those areas,” said William Schuler, Ph.D., a linguistics professor at The Ohio State University. “It’s figuring out what has happened rapidly, and that can involve automatically processing incident language.”
Now, researchers working on the project called Low Resource Languages for Emergent Incidents (LORELEI) are developing a grammar acquisition algorithm to discover the rules of lesser-known languages. Thanks to the new algorithm, the researchers who are led by Schuler can translate the lesser-known languages much easier and faster.
However, using this algorithm on a regular computer is not a good idea because learning different grammars from statistics requires tremendous power. That’s why the researchers are using a supercomputer – Ohio Supercomputer Center’s Owens Cluster – which enables them to increase the complexity of the model dramatically.
Ohio Supercomputer Center via Phys.org (https://phys.org/news/2017-11-linguistics-team-ohio-supercomputer-center.html)