close

Special Topics: Natural Language Processing with Deep Learning

The NLPwDL course provides in depth knowledge on Deep Learning methods in Natural Language Processing (NLP). It describes methods and architectures such as RNN, LSTM, Attentions, and Transformers, and studies them in NLP applications such as language modeling, document classification, machine translation, and abstractive/extractive summarization. Topics such as interpretability and energy consumption of NLP models as well as mitigating societal biases in NLP systems are discussed in the course.

Covered topics:

  • Document classification with Convolutional Neural Networks
  • Language modeling with Recurrent Neural Networks
  • Sequence to sequence for abstractive summarization with LSTM
  • Attention mechanism in seq2seq models
  • Transformers in neural machine translation
  • Contextualized word embeddings (BERT, GPT-x, etc.)
  • Interpretability, energy consumption, and compression of contextualized word embeddings
  • Measuring and mitigating societal biases in NLP

Information for the current semester (if available):

 

{{ labelInLang('cid') }} {{ labelInLang('title') }} {{ labelInLang('registration') }} {{ labelInLang('type') }} {{ labelInLang('hours') }} {{ labelInLang('teachers') }} {{ labelInLang('rhythm') }}
{{ item._id }} ({{ item.term }}) {{ item.title }}
{{ labelInLang('moreinfo') }}
{{ labelInLang('expand') }} {{ labelInLang('collapse') }}
{{ labelInLang('register') }} {{ item.type }} {{ item['hours-per-week'] }} {{ teacher.firstname }} {{ teacher.lastname }} {{ item.teachers.teacher.firstname }} {{ item.teachers.teacher.lastname }} {{ item.rhythm }}
{{ item._id }} ({{ item.term }})
{{ labelInLang('title') }} {{ item.title }}
{{ labelInLang('moreinfo') }}
{{ labelInLang('expand') }} {{ labelInLang('collapse') }}
{{ labelInLang('registration') }} {{ labelInLang('register') }}
{{ labelInLang('type') }} {{ item.type }}
{{ labelInLang('hours') }} {{ item['hours-per-week'] }}
{{ labelInLang('teachers') }} {{ teacher.firstname }} {{ teacher.lastname }} {{ item.teachers.teacher.firstname }} {{ item.teachers.teacher.lastname }}
{{ labelInLang('rhythm') }} {{ item.rhythm }}
 

Prerequisites:

  • It is strongly suggested to first pass the course Natural Language Processing (LVA Nr. 344.075). The NLP course provides all necessary prerequisties for NLPwithDL.  
  • Otherwise, if the NLP course is not taken ...
    • Python programming skill is mandatory.
    • Knowledge on machine learning, neural networks, and linear algebra is expected. 
    • Prior knowledge on deep learning is not required.