Uw huidige browser heeft updates nodig. Zolang u niet update zullen bepaalde functionaliteiten op de website niet beschikbaar zijn.
Let op: het geselecteerde rooster heeft overlappende bijeenkomsten.
Volgens onze gegevens heb je nog geen vakken behaald.
Je planning is nog niet opgeslagen
Let op! Uw planning heeft vakken in dezelfde periode met overlappend timeslot
Natural language generation (2025/2026: Periode 3)
Cursusdoel
Upon completion of this course, the student will have
- knowledge of the architecture of Natural Language Generation systems and the main tasks they perform
- knowledge of the linguistic and psycholinguistic underpinnings of different NLG tasks
- understanding of how neural network-based NLG models, including large language models, are designed and trained
- understanding of the decoding algorithms for generation with neural network-based NLG models
- knowledge of evaluation methods and metrics
- the ability to summarize and present a research paper on NLG
- exam (70% of the final mark)
- individual coursework (20%)
- group presentation (10%).
Vakinhoudelijk
This course studies the task of generating language automatically, from different types of input.
Examples include generating a summary of numerical data (for instance physiological parameters of a patient in a medical setting, or weather parameters for a weather report), or generating a description of an image.
Another example might be generating a response to a query, an increasingly common use case with large language models.
The generation of language involves many choices at different levels.
We therefore begin with an overview of “classical” NLG architectures and the various tasks they subsume, with a discussion of relevant linguistic and psycholinguistic insights.
We will then focus on more recent neural network architectures, from encoder-decoder to decoder-only models for text generation.
Here, we also pay attention to how such models are trained and finetuned, as well as the decoding algorithms for generating text stochastically.
Finally, we consider the challenges involved in evaluating NLG models using a variety of methods, from automatic metrics to task-oriented studies.
Course form
Lectures, presentations.
Literature
Most literature will be handed out during the course.
Examples include generating a summary of numerical data (for instance physiological parameters of a patient in a medical setting, or weather parameters for a weather report), or generating a description of an image.
Another example might be generating a response to a query, an increasingly common use case with large language models.
The generation of language involves many choices at different levels.
We therefore begin with an overview of “classical” NLG architectures and the various tasks they subsume, with a discussion of relevant linguistic and psycholinguistic insights.
We will then focus on more recent neural network architectures, from encoder-decoder to decoder-only models for text generation.
Here, we also pay attention to how such models are trained and finetuned, as well as the decoding algorithms for generating text stochastically.
Finally, we consider the challenges involved in evaluating NLG models using a variety of methods, from automatic metrics to task-oriented studies.
Course form
Lectures, presentations.
Literature
Most literature will be handed out during the course.
Werkvormen
Hoorcollege
Toetsing
Eindresultaat
Verplicht | Weging 100% | ECTS 7,5
Ingangseisen en voorkennis
Ingangseisen
Je moet een geldige toelatingsbeschikking hebben
Voorkennis
Er is geen informatie over benodigde voorkennis bekend.
Voertalen
- Engels
Cursusmomenten
Gerelateerde studies
Tentamens
Er is geen tentamenrooster beschikbaar voor deze cursus
Verplicht materiaal
-
WNBMost literature will be handed out during the course.
Aanbevolen materiaal
Er is geen informatie over de aanbevolen literatuur bekend
Coördinator
| prof. dr. A. Gatt | a.gatt@uu.nl |
Docenten
| prof. dr. A. Gatt | a.gatt@uu.nl |
Inschrijving
Deze cursus is open voor bijvakkers. Controleer wel of er aanvullende ingangseisen gelden.
Inschrijving
Van maandag 3 november 2025 tot en met vrijdag 21 november 2025
Na-inschrijving
Van maandag 19 januari 2026 tot en met zondag 15 februari 2026
Inschrijving niet geopend
Permanente link naar de cursuspagina
Laat in de Cursus-Catalogus zien
Laat in MyTimetable zien
klikt, stop je een vak in je rugzak, zodat je dit vak door de rest van de CursusPlanner mee kunt nemen.