This is the page of the course Natural Language Processing 1 offered at the University of Amsterdam

Course coordinators: Ekaterina Shutova and Wilker Aziz

Lab coordinator: Vera Neplenbroek

Senior teaching assistant: Fivos Tzavellos

Teaching assistants:

• Adrian Sauter
• Alisia Baielli
• Arne Eichholz
• Federica Valeau
• Ivo Verhoeven
• Iwo Godzwon
• Izabela Kurek
• Luan Fletcher
• Milan Miletic
• Oliver van Erven
• Teo Stereciu
• Wafaa Mohammed

Course registration

The course registration is now closed.

Content

This course introduces the fundamental techniques for a range of tasks in natural language processing (NLP), with a particular focus on statistical and deep learning approaches. We will consider tasks that involve hierarchical structure (e.g., syntactic trees) and/or hidden structure (e.g., in semantic tasks), using supervised and unsupervised learning algorithms. The course aims to explain the potential and the main limitations of these techniques, as well as discussing them in the wider context of current research issues in NLP and its real-world applications.

The lectures will cover the following topics:

• Introduction to NLP and its applications
• Language models
• Part-of-speech tagging
• Context-free grammars and syntactic parsing
• Lexical and distributional semantics
• Neural language models and word embeddings
• Compositional semantics and sentence representations
• Discourse processing
• Dialogue modelling
• Language generation
• Summarization and machine translation
• Large language models (LLMs)
• LLM pretraining and alignment
• Interpretability of NLP models

An important component of the course is a hands-on practical, in which the students will have the opportunity to implement a number of language processing methods and perform experiments on a real-world task: sentiment analysis of movie reviews. The hands-on-practical consists of two parts and will be completed in teams of two. You can find the link to the team registration form on the Canvas home page of this course.

Recommended reading

Jurafsky, D. & Martin, J. Speech and language processing. 3rd edition, available online. We will be referring to these online chapters throughout the course.

Assessment

• exam 30%
• practical 1 (group work) 20%
• practical 2 (group work) 30%
• pen-and-paper exercises 20%

Deadlines

Practical assignments are handled on Canvas, check there for accurate deadlines. Pen-and-paper exercises are handled on ANS, check there for accurate deadlines. For the exam, always check and trust the information on Datanose. With this disclaimer, the deadlines (as known at the beginning of the course) are listed below:

• Practical 1: 12 November
• Practical 2 and report: 19 December
• Exercises: 14 November, 20 November, 4 December
• Exam: 16 December