Kenton Murray is a 5th year PhD Candidate at the University of Notre Dame working with David Chiang on methods for improving Neural Machine Translation for Low-Resource and Morphologically Rich Language Pairs. Prior to ND, he was a Research Associate at the Qatar Computing Research Institute focusing on Arabic Machine Translation. He holds a Master’s in Language Technologies from Carnegie Mellon University and a Bachelor’s in Computer Science from Princeton University.​

In recent years, Neural Networks have reached state-of-the-art performance in a variety of NLP tasks, including Machine Translation. However, these methods are very sensitive to selecting optimal hyperparameters. Frequently this is done by large scale experimentation — often through grid or random searches. However, this is computationally expensive and time consuming. In this talk, I will present a few methods for learning hyperparameters during the training process. Thus, instead of training multiple networks with different hyperparameters, we only need to train one network without large grid search experiments. Our methods yield comparable, and often better, results, but at a faster experimentation rate.