Neural Networks for Natural Language Processing
AI technologies are revolutionising the way computers understand and use language and speech. The underlying models are constantly changing and new developments are finding their way into new applications at very short notice. This course deals with the use of neural networks in natural language processing applications, and gives an overview of different neural architectures that can be used to process text data.
Practical information:
Want to register?
- Register until: 23 Mar 2023
- Prerequisites: theory: no prior knowledge needed; hands-on sessions: need of basic knowledge of Python.
- Price: Profit sector: €300 (only theory: €100) | Non-profit sector: €180 (only theory: €70) | Researchers & PhD: €50 (only theory: free)
Georganiseerd door:
Course content
The theoretical session remains at an introductory level. For those who also join the hands-on sessions (max. 25 participants), prior knowledge of Python is a must.
Theory session: 9h30 – 12h30
- Different paradigms for NLP: symbolic, statistical, neural
- Preprocessing of document collections
- Word embeddings
- Use of language models
- An overview of neural architectures for text processing
- Continuous bag of words
- Convolutional neural networks
- Recurrent neural networks
- Transformer architectures
- Pretrained neural models and fine-tuning
- Transfer learning
- BERT for NLP classification
- Limitations of neural approaches
Lunch 12h30 - 13h30
Hands-on session: 13h30 – 16h
Here, the participants can gain (a first) hands-on experience with existing tools.
- Practical application
Learning outcomes
Participants
- Understand the principles and basic concepts of NLP;
- Have a better understanding of the use of AI on language data, both speech and text;
- Have acquired insight in the underlying language models used in speech and text analysis.
Registration
Registration is only complete when the fee has been paid. We will send you the invoice once your registration has been processed.
Cancellation policy: Cancellation free of charge (except for 10% administrative cost) will be possible till one week before the start of the course. After that date, cancellation free of charge will only be possible with a valid reason. If no valid reason is presented, no reimboursement will apply.
Teacher / speaker
Tim Van de Cruys
Tim Van de Cruys is associate professor at the Linguistics Department of the Faculty of Arts, KU Leuven. He has previously worked as a CNRS researcher at the IRIT computer science institute in Toulouse. His research field is computational linguistics. He investigates the automatic extraction of semantics from text, focusing mainly on methods of distributional similarity. He has published on factorization methods, tensor algebra, and neural architectures for language processing.
Methods in Language and Speech Technology
Artificial Intelligence technologies are revolutionizing the way computers understand and use language and speech. The underlying models are rapidly changing and new developments almost immediately find their way to new applications. In this course, we dive into the possibilities for sentiment analysis and the detection of emotions by AI-driven technology.
A growing number of people will come into contact with these applications when AI is implemented within their organisation. Knowing the possibilities and being able to work with the technological tools are crucial competences for the labour market of the future. The challenge is to accurately process the information in language and text, without losing the nuances and context.
VAIA developed, in collaboration with its partners, a course series on methods in language and speech technology.
Related courses
HPC Café
Seminarie - Online, Karlsruhe - KIT, HammerHAI, Training geselecteerd in de Belgische AI Factory Antenna (AIFA)
