Computational Linguistics

Catalog description

The application of computational methods to problems in natural-language processing. In particular we examine techniques due to recent advances in deep learning: word embeddings, recurrent neural networks (e.g., LSTMs), sequence-to-sequence models, and generative adversarial networks (GANs). Programming projects include sentiment classification, topic modelling and machine translation. Prerequisites are not strictly required, but the course will assume some knowledge of machine learning and deep learning, and will involve programming assignments in Python and PyTorch.