Download Data and Web Science Research Group - FIM

Semester Kick Off FSS 2016
Data and Web Science
Research Group
Universität Mannheim – DWS Research Group – Slide 1
Data and Web Science Research Group
5 Professors
9 Post-docs
18 PhD students
Universität Mannheim – DWS Research Group – Slide 2
Data and Web Science Research Group – Research Goal
Overall Research Goal:
Understand heterogeneous data in order to
improve applications using knowledge
Integrated
Schema.org Data
Integrated Web
Tables and Text Data
Applications
Data Mining & Reasoning
Data Integration
Information Extraction
Web
Search
Data
Analytics
Recommender
Systems
Process
Management
Universität Mannheim – DWS Research Group – Slide 3
Data and Web Science Research Group – Research Areas
- Artificial Intelligence (Prof. Heiner Stuckenschmidt)
• knowledge representation formalisms and reasoning techniques
for information extraction and integration
- Data Analysis (Prof. Rainer Gemulla)
• methods for analyzing and mining large datasets as well as their
practical realizations and applications
- Natural Language Processing (Prof. Simone Ponzetto)
• knowledge acquisition from heterogeneous Web sources and its
application to text understanding and search
Universität Mannheim – DWS Research Group – Slide 4
Data and Web Science Research Group – Research Areas
- Web-based Systems (Prof. Chris Bizer)
• technical and empirical questions concerning the evolution of the
World Wide Web from a medium for the publication of documents
into a global dataspace
- Web Data Mining (Prof. Dr. Heiko Paulheim)
• using web data as background knowledge in data mining, and data
mining methods to create and improve large-scale knowledge
bases
Universität Mannheim – DWS Research Group – Slide 5
Teaching Overview
The DWS Group offers the following courses for master students:
AI Seminar
Data and Web
Science Seminar
Team Project
Semantic Web
Technologies
Web Mining
Text Analytics
Hot Topics in
Machine Learning
Web Data
Integration
Data Mining II
Web Search and
IR
Data Mining and
Matrices
Knowledge
Management
Decision Support
Databases II
Data Mining I
Large-Scale Data
Management
Universität Mannheim – DWS Research Group – Slide 6
CS 661: Knowledge Management
LEARNING GOALS
- Ability to assess the value knowledge has for organizations
- Overview of knowledge management strategies
- Acquaintance with technical foundations of knowledge
management systems
- Information Retrieval and Text Mining
- Knowledge Representation: Repositories and Query Answering
- Collective Intelligence: Web 2.0 and Wikis, Social Networks
Programming skills and IT competence: practical usage of
technologies for knowledge acquisition and maintenance
Universität Mannheim – DWS Research Group – Slide 7
CS 661: Knowledge Management
- Lecturer: Prof. Dr. Simone Paolo Ponzetto
- Passing the course: Written Exam
- Optional: ungraded weekly assignments and tutorial lessons
to help you preparing for the written exam
Universität Mannheim – DWS Research Group – Slide 8
CS 560: Large-Scale Data Management
• What you need to know to work with Big Data
• Fundamental concepts and computational paradigms for large-scale
data management and Big Data
Universität Mannheim – DWS Research Group – Slide 9
CS 560: Large-Scale Data Management
• Computer Science Fundamental
• Instructors
• Prof. Dr. Rainer Gemulla (lecture)
• Kaustubh Beedkar (tutorium)
• Lecture
• Covers concepts, methods, systems
• Tutorium
• In-depth discussion and exercises
• Hands-on sessions and assignments
• All ungraded
●
If you plan to take the lecture, do it this term!
–
Lecture won‘t be offered next spring term (moves to winter term)
Universität Mannheim – DWS Research Group – Slide 10
IE 500: Data Mining 1
 „We are drowning in data, but starving for knowledge.“
(John Naisbitt, 1982)
But how do we get from data to knowledge?
 „Data mining is nothing else than torturing the data until it
confesses.“
(Fred Menger, year unknown)
Universität Mannheim – DWS Research Group – Slide 11
IE 500: Data Mining 1
 Lecture contents – the basics of “torturing data”:
• Classification: Will your bank grant you a loan?
• Frequent pattern mining: Which products to place together
in a supermarket to maximize customer purchases?
• Text Mining: Do students on Twitter like or dislike this lecture?
• Clustering: How to automatically organize your MP3 collection?
 Student project:
• Torture some data of your choice.
 Teaching staff:
• Prof. Dr. Christian Bizer (Lectures)
• Oliver Lehmberg, Kiril Gashteovski (Exercises)
Universität Mannheim – DWS Research Group – Slide 12
IE672: Data Mining 2
- Lecture covers advanced Data Mining methods
•
•
•
•
•
•
•
Regression and Forecasting
Dimensionality Reduction
Anomaly Detection
Time Series Analysis
Parameter Tuning
Ensemble Learning
Online Learning
- Organization:
• Lectures and Exercises
• Participation in Data Mining Cup
• Opportunity to become a certified RapidMiner Data Analyst
 Teaching staff:
• Prof. Heiko Paulheim (Lectures), Robert Meusel (Exercises)
Universität Mannheim – DWS Research Group – Slide 13
IE 671: Web Mining
- Cover specific methods for mining knowledge
from Web content and Web usage data:
1.
2.
3.
4.
5.
6.
7.
Web Usage Mining
Recommender Systems
Web Structure Mining
Social Network Analysis
Web Content Mining
Information Extraction
Sentiment Analysis
- Organization:
•. Lectures and Exercises
•. Student projects (second half of semester)
- Tools:
Universität Mannheim – DWS Research Group – Slide 14
IE 663: Web Search and Information Retrieval
- Understanding end-to-end search systems
Universität Mannheim – DWS Research Group – Slide 15
IE 663: Web Search and Information Retrieval
Instructor: Dr. Laura Dietz
Main Topics:
1. Information Retrieval
–
–
–
Boolean and vector space retrieval models
Probabilistic information retrieval
Evaluation of retrieval systems
2. Web search
–
–
Crawling
Link-based algorithms
3. Multimedia Information Retrieval
Universität Mannheim – DWS Research Group – Slide 16
CS 704: Process Mining Seminar
Topic
• Discovery, conformance, and enhancement of business processes
• more information is provided on our website: http://goo.gl/MdmnL8
Goals
• Read, understand, and explore scientific literature
• Summarize a current research topic in a concise report (10-15 pages)
Requirements
• No programming skills are required but they might be helpful
• Lectures such as Process Management are recommended
Schedule
• Select your preferred topics and register by Feb 29
Organizers
• Prof. Dr. Heiner Stuckenschmidt
• Timo Sztyler ([email protected])
Universität Mannheim – DWS Research Group – Slide 17
CS 707: Data and Web Science Seminar
• In this seminar, you will
• Learn about recent advancements in data and web science
• Read, understand, explore, and present scientific literature
• This term: neural networks for text analytics
• Yann LeCun, Facebook AI research lab: "The next big step for Deep Learning
is natural language understanding, which aims to give machines the power to understand
not just individual words, but entire sentences and paragraphs“
• Topics: Machine reading, machine translation, question answering, opinion mining, …
• Check out website
and register until
Wednesday
(Feb 17)
RNN for machine translation
• Instructors:
Kiril Gashteovski,
Rainer Gemulla
Universität Mannheim – DWS Research Group – Slide 18
Team Project „Footprints of the Smart City“
Optimization of Urban Services by IoT and Smart City Apps
Big Data
Analytics in IoT
Movement
Patterns
Accessible
Navigation
Traffic
Control
Energy Distribution
Public Transportation
Universität Mannheim – DWS Research Group – Slide 19
Team Project: Brainstorming and Clustering Tool
for Large-scale Meeting Moderations
Your Task:
Develop algorithms and
software that supports the
Director by observing and
making suggestions for how
to group ideas.
●
●
●
Partner: Teambits GmbH
Use techniques from Text
Analysis and Machine Learning.
Duration: 6 Months
Universität Mannheim – DWS Research Group – Slide 20
The DWS group continuously hires good students.
- To work on:
• Data and Web Mining projects
• Information Extraction and Integration projects
• Knowledge Representation and Reasoning projects
• Implement open source tools
- 30-60 h/month contracts are possible.
- Contact PostDoc or Professor responsible for the
project/area that you are interested in.
• Include CV and overview about your marks.
- Good start for writing your master thesis within group.
Universität Mannheim – DWS Research Group – Slide 21