Deep Learning For Natural Language Processing
Frequency
Every 2 years
Summary
This course covers advanced topics in deep learning architectures for natural language processing. The focus is on attention-based architectures, structure processing and variational-Bayesian approaches, and why these models are particularly suited to the properties of human language.
Content
Models and Methods
* Attention and Transformers
* Sequence-to-sequence and graph-to-graph models
* Multi-task and transfer learning
* Variational-Bayesian models and Diffusion
* LLMs, prompting, and RAG
Applications
* Language modelling
* Machine translation
* Text generation
* Knowledge extraction and embedding
* Dialogue systems
Keywords
Machine Learning, Natural Language Processing, Large Language Models.
Learning Prerequisites
Required courses
* Introductory course on Machine Learning.
* Undergraduate level probability, linear algebra, and programming.
Recommended courses
Courses on Natural Language Processing (Computational Linguistics, Human Language Technology), or Artificial Intelligence would be useful.
Learning Outcomes
By the end of the course, the student must be able to:
- Identify appropriate deep learning models and methods for different natural language processing tasks.ferent natural language processing tasks.
- Apply appropriate training, inference and evaluation methodology to such models.ogy to such models on large datasets using existing packages.
Assessment methods
Multiple.
In the programs
- Number of places: 40
- Exam form: Multiple (session free)
- Subject examined: Deep Learning For Natural Language Processing
- Courses: 28 Hour(s)
- TP: 28 Hour(s)
- Type: optional
- Number of places: 40
- Exam form: Multiple (session free)
- Subject examined: Deep Learning For Natural Language Processing
- Courses: 28 Hour(s)
- TP: 28 Hour(s)
- Type: optional