This course introduces computational linguistics and natural language processing (NLP) as the study and application of methods for working with human language using computers. It is designed for postgraduate diploma participants entering the field from linguistics, translation, education, computing, media, or other professional backgrounds. The course assumes no prior programming knowledge and introduces essential concepts through accessible explanations, worked examples, and guided online laboratories.

Participants begin with language as data, text normalization, and simple rule-based processing before encountering basic linguistic annotation and statistical approaches to text. They develop a first understanding of n-gram models, word representations, elementary text classification, neural language models, Transformers, and large language models (LLMs). Later sessions introduce prompting and retrieval-grounded question answering at a conceptual level, along with error analysis, limitations, and responsible use.

Short Python activities use supplied Google Colab notebooks and common libraries such as NLTK, spaCy, scikit-learn, and Hugging Face. Participants learn to read, run, and make limited changes to prepared examples; they are not expected to implement complex algorithms, train deep neural networks, fine-tune Transformer models, or deploy production systems. The course culminates in a supervised, small-scale project that uses an existing NLP tool or starter notebook to investigate a clearly defined question.