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.
Basics
1. Information Extraction
2.Information Retrieval
3. Topic Modelling
4. Word Embedding
5. seq2seq models
Large Language Models
6. Transformer: Architecture
7. Transformer: Applications
8. Large Language Models: Architecture, Pre-training and Fine-tuning
9. Efficient Transformers
10. Ethnical & Social concerns, Privacy, and Limitations of Large Language Models
Natural Language Generation and Evaluation
11. Machine Translation ( Multilingual NLP)
12. Text Summarization
13. Model Hallucination
14. Corpus-based Question Answering
Conversational AI / Conversational Interfaces
15. Task-based & Social Conversational Agents
16. Dialogue Management (Dialogue State Tracking & Policy)
17. Conversational Search Systems
Knowledge Graph in NLP
18. Graph Representations for NLP
19. Knowledge Graph-based Question Answering
Natural Language Inference
20. Natural Language Inference
LegalTech
21. Semantic Analysis of Legal Documents
22. LegalTech: Applications of Information Retrieval, Summarization and Simplification
Differential Privacy in NLP
23. Metric Differential Privacy in NLP
24. Privacy in Deep NLP
Explainability in NLP
25. Explainability in NLP
Session | Date | Topic |
-1 |
27.01.2023 11:00 - 12:00 |
Preliminary Meeting |
1 |
21.04.2023 10 am - 12 pm |
1) Introduction & workshop on paper writing 2) Information Extraction 3) Word Embedding |
2 |
28.04.2023 10 am - 12 pm |
1) Information Retrieval 2) Topic Modelling |
3 |
05.05.2023 10 am - 12 pm |
1) seq2seq models 2) Machine Translation ( Multilingual NLP) |
4 |
12.05.2023 10 am - 12 pm |
1) Transformer: Architecture 2) Large Language Models: Architecture, Pre-training and Fine-tuning |
5 |
19.05.2023 10 am - 12 pm |
1) Transformer: Applications 2) Efficient Transformers |
6 |
26.05.2023 10 am - 12 pm |
Guest Lecture Volkswagen |
7 |
02.06.2023 10 am - 12 pm |
1) Text Summarization 2) Corpus-based Question Answering |
8 |
09.06.2023 10 am - 12 pm |
1) Model Hallucination 2) Task-based & Social Conversational Agents |
9 |
16.06.2023 10 am - 12 pm |
1) Dialogue Management (Dialogue State Tracking & Policy) 2) Conversational Search Systems |
10 |
23.06.2023 10 am - 12 pm |
1) Graph Representations for NLP 2) Knowledge Graph-based Question Answering |
11 |
30.06.2023 10 am - 12 pm |
1) Natural Language Inference 2) Explainability in NLP |
12 |
07.07.2023 10 am - 12 pm |
1) Ethnical & Social concerns, Privacy, and Limitations of Large Language Models 2) Guest Lecture Munich RE |
13 |
14.07.2023 10 am - 12 pm |
1) Metric Differential Privacy in NLP 2) Privacy in Deep NLP |
14 |
21.07.2023 10 am - 12 pm |
1) Semantic Analysis of Legal Documents 2) LegalTech: Applications of Information Retrieval, Summarization and Simplification |
Prerequisites |
|
Presentations |
|
Project/Demo |
optional. 0.3 grade bonus |
Seminar Paper |
|
Peer Review |
|
Deliverable |
Deadline |
Format |
Final presentation slides |
Before your talk |
Powerpoint, Keynote or PDF |
Code for the project |
TBD |
.zip |
Seminar paper for peer review |
28.07.23 |
PDF based on provided LaTex template |
Peer review |
04.08.23 |
txt-File |
Revised seminar paper |
11.08.23 |
PDF based on provided LaTex template |
Name | Type | Size | Last Modification | Last Editor |
---|---|---|---|---|
Afzal NLP Seminar Kickoff 2023.pdf | 1,16 MB | 27.01.2023 | Anum Afzal |