Back to top

Natural Language Processing - Methods and Applications

Last modified Apr 15
   No tags assigned

People in organizations, society and institutions communicate via natural language. Typically, large amounts of unstructured information are stored in text documents. However, it is very challenging for machines to query relevant content fast and extract structured information.

Machine-based solutions for text analysis, indexing and generation are often summarized under the terms natural language processing, text mining or natural language generation. In the past decades, many different methods and solutions have been developed. The diversity of the different problems and the fast development of new technologies, e.g. machine learning, underline the large potential of these methods. 

The seminar aims to give an overview over the technological building blocks and their applications. The participants independently work on a scientific topic, based on existing literature and present and discuss their findings in a presentation and a seminar paper.

 

Important Dates

26.02.2019: Topic assignment

 

Seminar Topics

  1. Pre-processing of Natural Language in Source-Code (Nicholas, Christof)
  2. Context Aware Word Embedding (Hala, Ahmed)
  3. Relation Extraction (Erik, Daniel)
  4. Information Retrieval (Wenbin, Christof)
  5. Efficient Document / Information Retrieval through nearest neighbor search (Jiaxi, Christof)
  6. Readability (Anastasia, Daniel)
  7. Text Simplification (Martin M., Daniel)
  8. Natural Language Generation for Behaviour Change Support Systems (Wusheng, Daniel)
  9. Conversational Interfaces (Nika, Daniel)
  10. Evaluating NLG systems (Wei, Daniel)
  11. Automatic Traceability Maintenance via NLP techniques (Mürüvvet, Christof)
  12. Unsupervised Deep Learning for Translation (Wenjian, Ahmed)
  13. Few-Shot Learning (Martin W., Ahmed)
  14. Transfer Learning and domain adaptation for Deep Learning (Nino, Ahmed)
  15. Multi-Task Deep Learning (Oktav, Ahmed)

 

Weekly Sessions

Session Date Topic Room
-1

05.02.2019

17:00 - 18:00

Preliminary Meeting FMI 01.10.11
0

26.02.2019

14:00 - 15:00

Topic assignment

Organization

FMI 01.10.11
 

until 31.03.2019

Meeting with your advisor  
1

30.04.2019

14:00 - 16:00

Introduction to NLP

Pre-processing of Natural Language in Source-Code

FMI 01.10.11
2

07.05.2019

14:00 - 16:00

Context Aware Word Embedding

Relation Extraction

 FMI 01.10.11
3

14.05.2019

14:00 - 16:00

Information Retrieval

Efficient Document / Information Retrieval through nearest neighbor search

 FMI 01.10.11
4

21.05.2019

14:00 - 16:00

Readability

Text Simplification

 FMI 01.10.11
5

28.05.2019

14:00 - 16:00

Natural Language Generation for Behaviour Change Support Systems

Conversational Interfaces

 FMI 01.10.11
6

04.06.2019

14:00 - 16:00

Evaluating NLG systems

Automatic Traceability Maintenance via NLP techniques

 FMI 01.10.11
 

11.06.2019

Whitsun break

No seminar

 
7

18.06.2019

14:00 - 16:00

Unsupervised Deep Learning for Translation

Few-Shot Learning

 FMI 01.10.11
8 25.06.2019

14:00 - 16:00

Transfer Learning and domain adaptation for Deep Learning

Multi-Task Deep Learning

 FMI 01.10.11
9

02.07.2019

14:00 - 16:00

Wrap-up

FMI 01.10.11

 

Delivarables

Prerequisites

  • Regular attendance (not more than one missed session)
  • Active Participation during sessions

Presentations

  • 40 min:
    • 30 min presentation
    • 10 min discussion

Seminar Paper

  • 8 pages
  • Latex-Template provided on Moodle

Peer Review

  • 2 reviews of other seminar papers

Submissions

Deliverable

Deadline

Format

Final presentation slides

Before your talk

Powerpoint, Keynote or PDF

Seminar paper for peer review

14.07.2019

PDF based on provided LaTex template

Peer review

21.07.2019

txt-File

Revised seminar paper

28.07.2019

PDF based on provided LaTex template

Files and Subpages

There are no subpages or files.