Machine Learning for

Language Analysis

Late Summer School

// 26.9.–29.9.2018

© GaudiLab/shutterstock

 

 

 

 

// Program

© Laremenko Sergii/shutterstock

The Late Summer School mainly adresses students and doctoral candidates from linguistics and digital humanities, but participants from other fields who are interested in machine learning are welcome as well. Basic programming skills are required. The first part of the program consists of a basic introduction to machine learning for the analysis of natural languages. The second part deals with more specific questions from the field. We try to recruit lecturers for various topics, from theoretical background and its practical implementation.

 

< / >

Wednesday / Thursday   //  26./27.9.2018

 

learning Machine Learning

 

(Nils Reiter, IMS Stuttgart) - The theoretical basics of machine learning methods are presented in a mixture of hackaton and tutorial, including an example implementation in Python and the concrete evaluation of text-analytical methods within

the framework of a small shared task.

 

Soft requirements and installation instructions: see here.

Download the full program pdf here

 

 

 

Friday / Saturday // 28./29.9.2018

 

Machine Learning with audio and speech data

(Parallel session)

 

(Fraunhofer IAIS) - In the audio mining and speech recognition part, participants will be introduced to using machine learning to solve problems relation to audio data and in particular audio recording of speech. The participants will work with multilingual audio data and in particular focus on language independent problems such as speech detection, speaker diarization and related tasks. The course is based on an open source setup built on Keras (and Tensorflow).

Download the full program pdf here.

 

// registration

© smolaw/shutterstock

Friday / Saturday // 28./29.9.2018

 

Deep Learning with Text Data
(parallel session)

 

(IDH Cologne) - The workshop aims to apply deep neural networks (DNNs) on written text. After some theoretical introduction on DNNs, the participants will learn to solve classification problems with DNNs. The second part of the workshop will be a hands-on session that is about building a

text generator with a DNN.

All implementations will be written in Python.

 

Software Requirements:

Will be announced on the first day of the Late Summer School.

Download the full program pdf here.

 

Registration // contact

 

 

 

 

 

 

 

The application deadline was August 20th, all applicants have been informed about the results. Please note that only candidates who submitted the signed registration form in time can participate! For further question, please use our contact e-mail:

ml-school@uni-koeln.de

Additional information about the school including the detailed program can be downloaded here.

The School is organized in the framework of the University of Cologne's Competence Area III (CA3: Quantitative Modeling
of Complex Systems) and by Jürgen Hermes, Claes Neuefeind (Institut for Digital Humanities, UoC), and Felix Rau (Institute for Linguistics, UoC). The School will take place at the University
of Cologne; organizational details will be announced on this website and via e-mail after the application deadline (August 20). For any further questions, please contact
ml-school@uni-koeln.de.

 

Accommodation: Cologne offers various possibilities for affordable accomodation, ranging from youth hostels to hotels. You can look for a nice place to stay, e.g., at "Colognetourism"
or on Google Maps.

 

Fee: There is no registration fee for taking part in the school.

// organization