On completion of the course, you should be able to:

1. explain central concepts, models, and algorithms of NLP
2. implement NLP algorithms and apply them to realistic problems
3. evaluate NLP components and systems with appropriate methods
4. identify, assess, and make use of NLP research literature

For each intended learning outcome, there is a set of knowledge requirements describing what you need to demonstrate to earn a certain grade. You can find these knowledge requirements on the Examination page.

The course covers

• state-of-the-art algorithms for the analysis and interpretation of natural language
• relevant machine learning methods with a focus on deep neural networks
• validation methods
• NLP applications
• NLP tools, software libraries, and data
• NLP research and development

in the following areas: word representations, language modelling, sequence labelling, syntactic analysis, and machine translation.

The means of instruction for this course include video lectures, interactive sessions, tutored computer labs, and supervision in connection with a project. You are also expected to study independently, both individually and in groups. When you plan your time for the course, you should calculate approximately

• 36 hours to watch and revise the video lectures
• 12 hours to attend the interactive sessions
• 56 hours to prepare for, work on, and reflect on the labs
• 56 hours to plan, work on, and reflect on the project

The reading for this course consists of individual sections from the following books:

• Jacob Eisenstein. Introduction to Natural Language Processing. MIT Press, 2019. Pre-print version available online

• Daniel Jurafsky and James H. Martin. Speech and Language Processing. An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Draft chapters in progress, December 2021.

For follow-up and in-depth reading, we recommend the following:

• Emily M. Bender. Linguistic Fundamentals for Natural Language Processing: 100 Essentials from Morphology and Syntax. Synthesis Lectures on Human Language Technologies. Morgan & Claypool, 2013.

• Yoav Goldberg. Neural Network Models in Natural Language Processing. Synthesis Lectures on Human Language Technologies. Morgan & Claypool, 2017.

• Yue Zhang and Zhiyang Teng. Natural Language Processing. A Machine Learning Perspective. Cambridge University Press, 2021. Recommended for a mathematics-oriented account of the subject.