TU Berlin

Quality and Usability LabQuality and Usability

Inhalt des Dokuments

zur Navigation

Quality and Usability Seminar

Seminar
(2 SWS/3 LP; SoSe/WiSe mit wechselndem Thema)
LV-Nummer: 0434 L 905

Zeit: Montags 16:00-18:00, erstmals am 15.04. TEL 209
Raum: First date in TEL 209, all other dates Auditorium 1, Geb. TEL 20. Etage
Contact: babak.naderi[at]tu-berlin.de

Topic: Natural Language Processing
in collaboration with the Language Technology Research Department of DFKI

How to apply?
If you are eligible (i.e. having a Bachelor degree and hands on experience with machine learning and deep learning), you should talk part in the first meeting. There we make a list of candidates according to the general priority rules. In case there are more candidate than the offered positions, students will be selected randomly.

Sprache: English

Beschreibung:

Natural Language Processing (NLP, sometimes also referred as Human Language Processing and more recently as Human Language Understanding) comprises a wide range of topics dealing with the computational treatment of language including structural analysis (e.g., syntax, semantics), knowledge processing (e.g., analytics), language generation (e.g., machine translation), and communication (dialogue, chatbots). 

Techniques are today mostly data-based using Machine Learning (ML), but in some areas, also “classical” modeling is used. 

In this seminar we plan to cover the following topics (depending on attendees’ interests):

 

  • Machine Translation & Evaluation
  • Relation Extraction
  • Summarisation
  • ML in NLP
  • Deep Learning in NLP
  • Chatbots / dialogue systemes
  • Knowledge Graphs
  • Topic Modelling
  • Linguistic Linked Open Data / Resources in general
  • Training and Evaluation Data (Annotation, etc.)
  • Question Answering / Reading Comprehension
  • Linguistic Challenges for NLP

Tasks and additional Information:

As this seminar requires making yourself familiar with a potentially new topic, we welcome especially highly motivated students. Required prerequisites are:

  1. Practical experiences with Deep Learning and/or Statistical Machine Learning
  2. Bachelor degree

 

In addition:

  • The number of participants is limited to 26
  • Participant should perform literature research on a chosen topic and give a presentation on that

 

 

Navigation

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe