Department of Data Science and Knowledge Engineering
Advanced Natural Language Processing
How do I say, "Where is the next Italian restaurant" in Dutch? Can I get a summary of today’s lecture? When were artificial neural networks developed? Computers able to answer these questions are a long-time dream of humankind and currently, we see first programs to solve these problems. This course will provide the skills and knowledge to develop state-of-the-art (SOTA) solutions for these natural language processing (NLP) tasks. After a short introduction to traditional statistical approaches to NLP, the course will focus on deep learning techniques to solve these problems. In the first part of the course, we will investigate methods to model sequence labeling tasks like Named Entity recognition or Part- of-speech techniques. The second part of the lecture will focus on sequence-to-sequence models, a very powerful model to solve many NLP tasks like machine translation, summarization and question answering. In this course, major challenges when building the systems will be address: representing words in neural networks, neural network architectures to model language, methods to train complex models and algorithms to find the most probable output.
Papers published in top international conferences and journals in machine learning field.