Hackathon on Text Re-Use ‘Don’t leave your data problems at home!’
The Göttingen Centre for Digital Humanities will host a Hackathon targeted at students and researchers with a humanities background who wish to improve their computer skills by working with their own data-set.
Rather than teaching everything there is to know about algorithms, the Hackathon will assist participants with their specific data-related problem, so that they can take away the knowledge needed to tackle the issue(s) at hand. The focus of this Hackathon is automatic text re-use detection and aims at engaging participants in intensive collaboration. Participants will be introduced to technologies representing the state of the art in the field and shown the potential of text re-use detection. Participants will also be able to equip themselves with the necessary knowledge to make sense of the output generated by algorithms detecting text re-use, and will gain an understanding of which algorithms best fit certain types of textual data. Finally, participants will be introduced to some text re-use visualisations.
Organised by: Emily Franzini, Greta Franzini and Maria Moritz
Who can apply / Eligibility
- The Hackathon is intended for an audience with a background in one or more humanities subjects, including Classics, History, Philosophy or similar.
- Masters and PhD students interested in Digital Humanities, and who plan to adopt text re-use technologies in their dissertations, would perfectly fit the participant’s profile.
- Participants should attend the Hackathon equipped with their own laptop, their own data-set and bring along questions, problems and wishes related to it.
- Participants should have good knowledge of English.
To ensure that every participant gets the right amount of individual assistance, the places will be limited to a maximum of 20.
Deadline for application
May 15th, 2015. No deadline extensions granted.
How to apply
To apply for a place, please email your CV and a letter of motivation to the contact address below, in PDF format. The letter of motivation should not exceed one A4 page and should include details regarding:
- your background (including information about your specific interests, e.g. language, time period, geographical area, etc.);
- reason for applying to this Hackathon;
- your research question(s);
- what you hope to take away from this Hackathon;
- the data you would bring with you to the Hackathon;
- where did you hear about this Hackathon.
Please use “Hackathon application 2015” as the email subject line of your application.
A small budget for students is available for travel reimbursements upon request.
The main purpose of the Göttingen Hackathon of July 2015 is to help participants uncover some of the mysteries that lie behind the software tools that allow us to make research with our data. For this reason, we will be ‘unpacking’ one such tool – the TRACER – which is based on a framework made up of algorithms for different components. These are: Segmentation, Pre-processing, Featuring, Selection, Linking, Scoring and Post-processing. Participants will be able to learn about how each step works and how to feed their own data into the pipeline. It will also be possible for participants to run their data only through the components which will help answer their own specific research questions. This exercise will explain the challenges that computer scientists face when transforming research questions about texts into algorithms able to generate coherent answers. It will also show how certain algorithms make sense only when used with certain types of data, so that participants can go home with an understanding of what works for them in terms of speed and quality of output.
We look forward to reading your application!
The eTrap Team
Project Website: http://etrap.gcdh.de/
Göttingen Centre for Digital Humanities (GCDH)
Papendiek 16, D-37073 Göttingen, Germany