This course covers both the fundamental and advanced topics in Natural Language Processing(NLP), which deals with the application of computational models to text data. In this course, the core tasks in natural language processing will be examined, including minimum edit distance, language modelling, Nävie Bayes, Maximum Entropy, text classification, sequence labelling, POS tagging, syntax parsing and computational lexical semantics. Modern NLP applications will be explored such as information retrieval, and statistical machine translation. Students will learn how to formulate and investigate research questions on related topics

CILO-1: Apply statistical models, such as N-Gram, to natural language processing tasks. CILO-2: Analyse and compare different classification models for natural language processing, including generative and discriminative models, Naïve Bayes, and sequence labelling models. CILO-3: Evaluate the IBM and phrase-based translation models and understand their applications in statistical machine translation. CILO-4: Apply neural networks, including deep neural networks and recurrent neural networks, for language modelling and machine translation.