Language Detection in the Wild

There are a host of freely available, pre-trained off-the-shelf language detection libraries, and many Social Media providers provide their own language detection in meta-data. This month, Shailesh Vedula will present the results of a study he performed comparing off-the-shelf models with custom models trained on real-world, domain-specific data. He will also present methods for determining performance on real-world data such as Twitter

Shailesh Vedula is a graduate student in the department of Industrial and Operations Engineering at the University of Michigan. He is passionate about machine learning and natural language processing especially its application to the medical field. He interned at Digital Roots the summer.