Admission requirements
The course is open to students with interest in applying modern AI methods to the analysis of language. Some exposure to Python, computational linguistics and statistics is preferred, but not required.
This course is desiged for students from the BA Linguistics. If it’s full, Linguistics students take priority.
Description
In this course, students will learn to apply deep learning methods to the analysis of natural language. We will discuss vectorized representations of texts (using a.o. word2vec and the recent BERT models), and we will apply neural networks to a variety of practical problems, including sentiment analysis, topic labeling, authorship attribution and question answering.
The course consists of lectures and practica. In the lectures, we will discuss the formal background of deep learning-based natural language processing, and recent relevant literature. In the practica, students will use an online environment (Google Colab) in which they can run their experiments. The practica begin with a short introduction to Python, limited to the fragment necessary to run the experiments (using the Keras deep learning library).
Students will be evaluated through (1) a written exam (2) a practical assignment consisting of an implementation of an NLP topic. This assignment will result in an online notebook that contains all steps and information to verify the approach and the outcomes. Topics for the assignment are voluntary, and will be chosen around the middle of the semester, so that students can get assistance during the practica.
Course objectives
This course will teach students the fundamentals of deep learning methods for natural language processing (NLP), and will instill practical skills for implementing basis deep learning-based NLP systems. We will stay away from the intense mathematics of deep learning (although some of it will be discussed where necessary). After successful completion of the course, students are able to convert text into vectorized representations, and are able to apply deep learning-based algorithms to these representations. They will be able to understand from a functional perspective current literature on deep learning-based NLP.
Timetable
Visit MyTimetable.
Mode of instruction
Lecture: 13 (1 hour each)
Research: 13 practicum sessions (2 hours each)
Assessment method
Written examination with short open questions
Take home examination : a final practicum assignment, consisting of an implementation of an NLP topic, proposed by the students themselves. Submitted as an online notebook with step-by-step analysis.
Assessment
Assessment consists of scoring the answers to the written exam, and grading the practical assignment. The assignment will be scored for effectiveness (the code should work and perform the intended operation) and clarity of exposure in the notebook (understandable comments and a step-by-step illustration of the working of the code).
Weighing
The final grade will consist of an unweighted average of the scores for the written exam and the practicum. Both components should score sufficiently and do not compensate for each other.
Resit
The resit for the written exam will consist of an alternative partial written exam readdressing the topics of the failed questions. The resit for the practicum will consist of a resubmission of the online notebook taking into account the comments by the teacher.
Inspection and feedback
How and when an exam review will take place will be disclosed together with the publication of the exam results at the latest. If a student requests a review within 30 days after publication of the exam results, an exam review will have to be organized.
Reading list
Stephan Raaijmakers: Deep learning for Natural Language Processing. Manning, 2020. Apply to teacher for eventually student discount.
Literature (papers), to be distributed at the onset of the course.
Python: http://www.spronck.net/pythonbook/index.xhtml
Registration
Enrolment through uSis is mandatory.
General information about uSis is available on this website.
Registration Studeren à la carte and Contractonderwijs
not applicable
Contact
For questions related to the content of the course, please contact the lecturer, you can find their contact information by clicking on their name in the sidebar.
For questions regarding enrollment please contact the Education Administration Office Reuvensplaats
E-mail address Education Administration Office Reuvensplaats: osz-oa-reuvensplaats@hum.leidenuniv.nl
For questions regarding your studyprogress contact the Coordinator of Studies
Remarks
not applicable