Event

• D. Jurafsky, J.H. Martin, Speech and Language Processing, 2nd ed. Pearson Int., 2009.
• A. Hogan, The Web of Data, Springer, 2020. 
• G. Rebala, A. Ravi, S. Churiwala, An Introduction to Machine Learning, Springer, 2019. 

The amount of information available today has surpassed all limits. The advent of large language models, such as Chat-GPT, has only exacerbated the situation. How can we trust all the information we come across on the web? How exactly does a large language model operate? Is there a way to clarify, evaluate, and authenticate this information? To transform raw data into well-organized knowledge, essential technologies such as natural language processing (NLP), knowledge graphs, and machine learning must be utilized. In this lecture, you will learn the fundamentals of NLP, as well as the basics of knowledge graphs and machine learning. This will enable you to transition from unstructured data to machine-processable knowledge.

- The Art of Understanding

- Natural Language Processing

• NLP and Basic Linguistic Knowledge
• NLP Applications, Techniques & Challenges
• Evaluation, Precision and Recall
• Regular Expressions 
• Tokenization
• N-gram Language Models
• Text classification
• Part-of-Speech Tagging
• Distributional Semantics & Word Embeddings

- Knowledge Graphs

• Knowledge Representations and Ontologies
• Resource Description Framework (RDF)
  as simple Data Model
• Creating new Models with RDFS
• Querying RDF(S) with SPARQL
• More Expressivity via Web Ontology Language (OWL)
• Quality Assurance with SHACL
• From Linked Data to Knowledge Graphs
• Wikipedia, DBpedia, and Wikidata

- Basic Machine Learning

• Machine Learning Fundamentals
• Evaluation and Generalization Problems
• Linear Regression
• Decision Trees
• Unsupervised Learning
• Neural Networks and Deep Learning

- ISE Applications

• Data Mining & Information Visualization 
• Knowledge Graph Embeddings
• Knbowledge Graph Completion
• Semantic Search
• Exploratory Search
• Semantic Recommender Systems
  
  

Learning objectives:

• The students know the fundamentals and measures of information theory and are able to apply those in the context of Information Service Engineering.
• The students have basic skills of natural language processing and are enabled to apply natural language processing technology to solve and evaluate simple text analysis tasks.
• The students have fundamental skills of knowledge representation with ontologies as well as basic knowledge of Semantic Web and Linked Data technologies. The students are able to apply these skills for simple representation and analysis tasks.
• The students have fundamental skills of information retrieval and are enabled to conduct and to evaluate simple information retrieval tasks.
• The students apply their skills of natural language processing, Linked Data engineering, and Information Retrieval to conduct and evaluate simple knowledge mining tasks.
• The students know the fundamentals of recommender systems as well as of semantic and exploratory search.