LING 575 L: Topics in Computational Linguistics

DEEP LEARNING FOR NATURAL LANGUAGE PROCESSING THE APPLICATION OF NEURAL NETWORK METHODS---UNDER THE NAME "DEEP LEARNING"---HAS LED TO BREAKTHROUGH IN A WIDE RANGE OF FIELDS, INCLUDIN IN BUILDING LANGUAGE TECHNOLOGIES (E.G. FOR SEARCH, TRANSLATION, TEXT INPUT PREDICTION). THIS COURSE WILL PROVIDE A HANDS-ON INTRODUCTION TO USE OF DEEP LEARNING METHODS FOR PROCESSING NATURAL LANGUAGE. METHOD TO BE COVERED INCLUDE STATIC WORD EMBEDDINGS, CONVOLUTIONAL NEURAL NETWORKS FOR TEXT, RECURRENT NEURAL NETWORKS, TRANSFORMERS, PRE-TRAININ AND TRANSFER LEARNING, WITH APPLICATIONS INCLUDING PARSING, TRANSLATION, AND GENERATION.