Machine learning for statistical NLP: introduction

About this programme

No fees are charged for EU and EEA citizens, Swedish residence permit holders and exchange students. This course introduces students to the principles and practices of machine learning in Natural Language Processing (NLP). It provides a solid foundation in the statistical and mathematical concepts underlying modern language technologies, combining theoretical understanding with practical experience in data analysis and model development. Students learn how to represent linguistic data for machine learning, design data pipelines, and apply standard algorithms such as support vector machines, logistic regression, and basic neural networks. The course emphasizes hands-on experimentation using established NLP and machine learning toolkits, as well as good scientific practices and documentation. Understand how linguistic data is used in NLP applications and the mathematical foundations behind them. Apply and evaluate common statistical and machine learning techniques for NLP tasks. Selection is based upon the number of credits from previous university studies, maximum 165 credits. The Faculty of Humanities is located in the Humanisten building at Renströmsgatan 6. The Department of Philosophy, Linguistics and Theory of Science has its premises on the 5th floor. Both the Faculty of Humanities and the adjacent Humanities Library offer several study areas and group rooms.