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 that describe what you need to demonstrate in order to earn a certain grade. These knowledge requirements can be found 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 course is given in the form of 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 course is co-taught with TDDE09 Natural Language Processing at the Faculty of Science and Engineering.

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.

What you can expect from us. We try our best to give you prompt, constructive, and meaningful feedback on how well you meet the knowledge requirements set out for the course. We offer feedback in various forms; you can find the details on the Examination page. Our focus is on formative feedback, which you can use to improve your learning (and we can use to improve our teaching!) while the course is ongoing.

What we expect from you. We expect you to familiarise yourself with the knowledge requirements set out for the course and to actively seek our feedback on how well you meet these requirements. We also expect you to reflect on the feedback we provide, and grasp opportunities to put it to good use.

What we expect from you. This webpage is the primary source of information about the course, and we expect you to keep yourself up-to-date with what we publish here. We also send out information via the University’s email list for the course, and we expect you to read email from this list regularly while the course is ongoing.

What you can expect from us. When you contact us via email, you can expect an answer during standard working hours, 8–17. (We do not respond to email in the evening or on the weekend.) For more personal contact, you can book an appointment with the examiner on Teams.