Konu özeti

• Konu seçin General

  General

  Hepsini daralt Hepsini genişlet

  Target audience: The course is recommended for master students of all CS-oriented programs (Master Informatik, Master eXtended AI, Master Business Informatics). Prior knowledge of core NLP and machine learning concepts is desirable, albeit not mandatory. 

  Credits: 5 ECTS

  Lectures: Wed, 10.15-11.45 in Übungsraum I (ÜR I, Informatikgebäude)

  Exercises: Fri, 14.15-15.45 in Übungsraum I (ÜR I, Informatikgebäude)

  Examination: written or oral exam (depends on the number of students, it will be fixed and announced after the first two weeks of lectures)

  
  

  • Announcements etkinliğini seçin

    

    Announcements Forum
  • Discussion forum etkinliğini seçin

    

    Discussion forum
• Konu seçin Lectures

  Lectures
  • Lecture 1: Language Diversity (+Course Organization) etkinliğini seçin

    

    Lecture 1: Language Diversity (+Course Organization) Dosya
  • Lecture 2: Neural Language Modeling & Tokenization etkinliğini seçin

    

    Lecture 2: Neural Language Modeling & Tokenization Dosya
  • Lecture 3: Training Deep NNs etkinliğini seçin

    

    Lecture 3: Training Deep NNs Dosya
  • Lecture 4: Transformer etkinliğini seçin

    

    Lecture 4: Transformer Dosya
  • Lecture 5: Cross-Lingual Word Embeddings etkinliğini seçin

    

    Lecture 5: Cross-Lingual Word Embeddings Dosya
  • Lecture 6: Cross-Lingual Transfer etkinliğini seçin

    

    Lecture 6: Cross-Lingual Transfer Dosya
  • Lecture 7: Curse of Multilinguality etkinliğini seçin

    

    Lecture 7: Curse of Multilinguality Dosya
  • Lecture 8: Word Alignment and Label Projection etkinliğini seçin

    

    Lecture 8: Word Alignment and Label Projection Dosya
  • Lecture 8 (Word alignment): Recording etkinliğini seçin

    

    Lecture 8 (Word alignment): Recording URL
  • Lecture 9: Text Generation (with NMT focus) etkinliğini seçin

    

    Lecture 9: Text Generation (with NMT focus) Dosya
  • Lecture 10: (Multilingual) Sentence Encoders etkinliğini seçin

    

    Lecture 10: (Multilingual) Sentence Encoders Dosya
• Konu seçin Project

  Project
  • Submission project presentation and code etkinliğini seçin

    

    Submission project presentation and code Ödev
• Konu seçin Exercises

  Exercises
  • Exercise 01 etkinliğini seçin

    

    Exercise 01 Dosya
  • Exercise 02 etkinliğini seçin

    

    Exercise 02 Dosya
  • Exercise 03 etkinliğini seçin

    

    Exercise 03 Dosya
  • Exercise 04 etkinliğini seçin

    

    Exercise 04 Dosya
  • Projects etkinliğini seçin

    

    Projects Dosya
  • Exercise 05 - Parameter-Efficient Fine-Tuning etkinliğini seçin

    

    Exercise 05 - Parameter-Efficient Fine-Tuning Ödev
  • Exercise 05 - Parameter-Efficient Fine-Tuning - Solutions etkinliğini seçin

    

    Exercise 05 - Parameter-Efficient Fine-Tuning - Solutions Dosya
  • Exercise 06 - Token-Level Transfer etkinliğini seçin

    

    Exercise 06 - Token-Level Transfer Ödev
  • Exercise 06 - Token-level Transfer - Solutions etkinliğini seçin

    

    Exercise 06 - Token-level Transfer - Solutions Dosya
  • Exercise 07 - Neural Machine Translation etkinliğini seçin

    

    Exercise 07 - Neural Machine Translation Ödev
  • Exercise 07 - Neural Machine Translation - Solutions etkinliğini seçin

    

    Exercise 07 - Neural Machine Translation - Solutions Dosya
  • Exercise 08 - Sentence Representation Learning etkinliğini seçin

    

    Exercise 08 - Sentence Representation Learning Ödev
  • Exercise 08 - Sentence Representation Learning - Solutions etkinliğini seçin

    

    Exercise 08 - Sentence Representation Learning - Solutions Dosya
• Konu seçin Course content

  Course content

  This is planned/tentative content. As such it is still subject to change, that is, modifications both with respect to the topics and order of lectures are possible. 

  Date	Lecture	Blocks
  26.4.	L1: Languages of the world & Linguistic Universals; Course organization	Introduction
  10.5.	L2: Language modeling, word embedding models, vocabulary & tokenization	Block I: Fundamentals
  17.5.	L3: Training Deep LMs — Gradient Descent, Backprop, Batching, Dropout…	Block I: Fundamentals
  24.5.	L4: Transformer Almighty & Pretraining Language Models	Block I: Fundamentals
  31.5.	L5: Multilingual Word Embedding Spaces	Block II: Multilinguality
  7.6.	L6: Multilingual LMs and CL Transfer, Multilingual Evaluation	Block II: Multilinguality
  14.6.	L7: Curse of Multilinguality, Modularization, and Language Adaptation	Block II: Multilinguality
  28.6.	L8: Transfer for Token-Level Tasks: Word Alignment & Label Projection	Block II: Multilinguality
  5.7.	L9: Neural Machine Translation	Block III: Advanced
  12.7.	L10: Multilingual Sentence Representations	Block III: Advanced
  19.7.	L11: Prompting and LLMs; ChatGPT/GPT-4	Block III: Advanced

  
  

  
  
• Konu seçin Exams

  Exams
  • Exam Results (Klausur, 20.7.2023) etkinliğini seçin

    

    Exam Results (Klausur, 20.7.2023) Dosya