Modulbeschreibung

Deep Dive in Natural Language Processing: Word Embeddings, Sequence2Sequence Models, Transformers an

Kurzzeichen:
M_TuIT_EVA_1014
ECTS-Credits:
3
Leitidee:

The students

  • learn the theory and application of DL models used in NLP.
  • understand the key concepts of the DL approach to NLP.
  • get to know a wide sample of possible application examples.
  • learn how to approach their own NLP projects.
  • get the skills in Python and Tensorflow to work on Dl-based NLP projects.
Modulverantwortung:
Würsch Christoph
Standort (angeboten):
Buchs
Modultyp:
Wahlpflicht-Modul für MSE Master of Science in Engineering BB STD_08 (BU)(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Wahlpflicht-Modul für MSE Master of Science in Engineering BB STD_13 (BU)(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Wahlpflicht-Modul für MSE Master of Science in Engineering BB STD_16 (BU)(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Wahlpflicht-Modul für MSE Master of Science in Engineering VZ STD_08 (BU)(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Wahlpflicht-Modul für MSE Master of Science in Engineering VZ STD_13 (BU)(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Wahlpflicht-Modul für MSE Master of Science in Engineering VZ STD_16 (BU)(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Wahlpflicht-Modul für Technik und IT MSE_20(Keine Semesterempfehlung)Kategorie:Fachliche Vertiefung (MSE-FachV)
Modulbewertung:
Note von 1 - 6

Leistungsnachweise und deren Gewichtung

Während der Unterrichtsphase:

Deliverable: Didactically successful introduction to "Natural Language Processing and its Applications" in the form of one or several Jupyter notebooks with exemplary, directly executable Python code (language: English).

Bewertungsart:
Note von 1 - 6
Gewichtung:

Deliverable: Didactically successful introduction to "Natural Language Processing and its Applications" in the form of one or several Jupyter notebooks with exemplary, directly executable Python code (language: English).

Bemerkungen:

Inhalte

Angestrebte Lernergebnisse (Abschlusskompetenzen):

The students

  • learn the theory and application of DL models used in NLP.
  • understand the key concepts of the DL approach to NLP.
  • get to know a wide sample of possible application examples.
  • learn how to approach their own NLP projects.
  • get the skills in Python and Tensorflow to work on Dl-based NLP projects.
Modul- und Lerninhalt:

Einleitung:

Natural Language Processing (NLP) develops statistical techniques and algorithms to automatically process natural languages (such as English). It includes a number of AI areas, such as text understanding and summarization, machine translation, and sentiment analysis. This course introduces the foundations of technologies in NLP and their application to practical problems. It brings together the state-of-the-art research and practical techniques in NLP, providing students with the knowledge and capacity to conduct NLP research and to develop NLP projects.

 

Lerninhalte:

  • Handling and pre-processing of textual and speech data (regex)
  • Bag-of-word models
  • Word embeddings / text representations
  • Basics of neural network and deep learning for NLP
  • Basics of recurrent neural networks
  • Study and apply theory and skills to problems such as:
    o text classification
    o semantic analysis
    o Language and topic modelling
    o Part-of-speech tagging
    o Sentiment Analysis
    o Machine Translation
  • Study and work on a specific NLP project