Natural language processing (NLP) is a branch of artificial intelligence that deals with computational approaches used to process text.

Human language (i.e., natural language) is inherently ambiguous. Ambiguity resolution using computational techniques is at the heart of NLP. As a result, the advancements in NLP can be visualized as three generations: rule-based, statistical and neural. The course introduces the three generations of NLP through the philosophy of ambiguity resolution being the core task of NLP. The content covers different NLP sub-problems (such as POS tagging, sentiment classification, named entity recognition, machine translation and summarisation), and typical approaches in the three generations to tackle these sub-problems.

With recent advancements in large language models, there has been a renewed interest in NLP from industry and research alike. However, NLP precedes large language models. The exposition of NLP centered around ambiguity resolution helps to develop an understanding of the past and the present of NLP.