An introduction to the computer processing of written natural language, covering core concepts, models, and algorithms for analysing and processing natural language data, exploring contemporary NLP systems, and discussing their strengths, limitations, and applications.

Explores why computer speech processing is an important and difficult problem, investigating speech representation in articulatory, acoustic, and auditory domains. Takes a multi-disciplinary approach drawing on linguistics, phonetics, and psychoacoustics, with digital signal processing foundations.

Introduces the principles of speech technology, including automatic speech recognition using statistical modelling, speech synthesis and text-to-speech methods in spoken language systems. Includes project work involving implementation and assessment of a speech technology device.

Covers core technologies underpinning modern artificial intelligence, introducing statistical machine learning and probabilistic modelling and their application to describing real-world phenomena. Provides grounding in state-of-the-art algorithms that allow computer systems to learn from data.

Introduces fundamental concepts in natural language text processing, covering techniques for handling text corpora and examining systems that require automated processing of large volumes of text. Focuses on modern quantitative techniques for text analysis and models for acquiring information from texts.

A research-led individual project supervised by a member of staff, completed during the summer. You can choose from a wide range of topics in areas such as machine learning, natural language processing, or speech recognition, with options to work within the university or at an industrial partner.