TRACER tutorial, Göttingen, May 2017!

We’re excited to announce that eTRAP will be giving its next text reuse tutorial as a pre-conference workshop of the Datech International Conference being held in Göttingen, Germany!

The tutorial will run on 30th May at the Göttingen Centre for Digital Humanities (GCDH) of the University of Göttingen.

The tutorial builds on eTRAP’s research activities, most of which deploy our TRACER machine. TRACER is a suite of algorithms aimed at investigating text reuse in different corpora, be those prose, poetry, in Italian, Latin, Ancient Greek or medieval German. TRACER provides researchers with statistical information about the texts germany-652967_1280under investigation and its integrated reuse visualiser, TRAViz, displays the reuses in a more readable format for further study.

This tutorial is for anyone wishing to independently understand, use and run TRACER on his/her own data. For the purpose of the tutorial, participants will initially be working on an English data-set provided by eTRAP. Depending on the overall progress, we may also allocate some time for investigating the participants’ own data-sets! For more information about previous editions of this tutorial, visit our Events page.

If you’re interested in exploring text reuse between two or multiple texts (in the same language) and would like to learn how to do it semi-automatically, then this tutorial is for you! In order to provide everyone with adequate (technical) assistance, the workshop can only accommodate 15 participants. To apply to the tutorial, please send a short CV and a brief motivation letter to contact(at)etrap(dot)eu by 30th April 2017. Those accepted will have to register for the conference at http://ddays.digitisation.eu/registration/

In summary:
WHAT: TRACER tutorial for computational text reuse detection
WHEN: 30th May 2017, 9am-6pm
WHERE: GCDH, Seminar Room 1 (ground floor), Heyne Haus, Papendiek 16, 37073 Göttingen, Germany
WHO: For humanists and computer scientists alike who bring their own laptop
HOW MANY: Maximum of 15 participants
HOW: You may attend by applying to the email address provided and then registering to the conference. Registration to the conference is necessary for attending the workshop.  There will be an extra charge of €50 for catering at the workshop and to receive the conference pack
LANGUAGE: The workshop will be in English, with assistance in German should it be necessary
OTHER: You will receive very clear instructions on what to bring and prepare before the workshop

We look forward to seeing you in Göttingen!

TRACER tutorial, Rome 2017

Photo of a fingerprintWe’re very pleased to announce that eTRAP will be giving a text reuse tutorial in collaboration with DiXiT at the annual conference of the Italian Association for Digital Humanities (AIUCD) in Rome, Italy, this coming January!

The tutorial will run on 23rd and 24th January at the Sapienza University in Rome.

The tutorial builds on eTRAP’s research activities, most of which deploy our TRACER machine. TRACER is a suite of algorithms aimed at investigating text reuse in multifarious corpora, be those prose, poetry, in Italian, Latin, Ancient Greek or medieval German. TRACER provides researchers with statistical information about the texts under investigation and its integrated reuse visualiser, TRAViz, displays the reuses in a more readable format for further study.

This tutorial seeks to teach participants to independently understand, use and run TRACER. For the purpose of the tutorial and to ensure the smoothest possible outcome, participants will initially be working on an English data-set provided by eTRAP. Depending on the overall progress, we may also allocate some time to investigating the participants’ own data-sets, provided these comply with the TRACER format. A detailed description of the tutorial can be DOWNLOADED HERE.

The workshop will be conducted in English, with assistance in Italian should it be necessary. For more information about previous editions of this tutorial, visit our Events page.

Eligibility, Requirements and Bursaries

If you’re interested in exploring text reuse between two or multiple texts (in the same language) and would like to learn how to do it semi-automatically, then this tutorial is for you. In order to provide everyone with adequate (technical) assistance, the workshop can only accommodate 12 participants. To apply to the tutorial, please send a short CV and a brief motivation letter to contact(at)etrap(dot)eu by 16th December 2016. Those accepted will have to register for the AIUCD conference at https://www.conftool.net/aiucd2017/

La Sapienza University makes available travel bursaries for early career researchers, who submit an abstract to the EADH day. Should you be eligible for the bursary and wish to attend our tutorial, you must submit both an abstract to EADH and a CV with motivation letter to eTRAP. You may also apply for the tutorial without an EADH submission but you will not be eligible for a bursary in that case.

We look forward to seeing you in beautiful Rome!

Transkribus: A User Report

Melina Jander, an eTRAP Research Assistant, has written a short user report on our experience with the Handwritten Text Recognition (HTR) tool Transkribus. We’re currently using Transkribus as part of our pilot project TrAIN (Tracing Authorship In Noise), which aims at defining the noise-threshold that affects computational analyses on HTR’d and OCR’d texts . How much noise do we have to correct? How much can we leave in?

The report describes progress made thus far. A second report will be published in 2017 to report on Transkribus‘ automation process on our data.

You can download the report from our Output page.

2016-11-04 Update: The Transkribus website advertises our user report here.

Book chapter: A Catalogue of Digital Editions

Book coverThe latest Digital Humanities monograph published by Open Book Publishers, Digital Scholarly Editing: Theories and Practices, includes a chapter written by Greta together with Melissa Terras and Simon Mahony from the UCL Centre for Digital Humanities. The chapter is entitled A Catalogue of Digital Editions and reports on an homonymous ongoing project that collects and analyses digital editions in an attempt to identify best practice in digital scholarly editing.

As an Open Access publication, you can download the entire volume for free!

Greta will be presenting the Catalogue of Digital Editions project in the form of a poster at the upcoming Text Encoding Initiative conference in Vienna.

Invited talk: “Beyond Word Clouds: Combining Entities and Topics for Fine-Grained Analyses of Historical Texts”

Please spread the word!

Speakers: Simone Ponzetto, Hiram Kümper, Federico Nanni (University of Mannheim)
Title: 
Beyond Word Clouds: Combining Entities and Topics for Fine-Grained Analyses of Historical Texts

Date: August 25th 2016, 12 PM – 1 PM
Location: Seminar room 1, Papendiek 16 (Heynehaus), Göttingen

Abstract: 

Future historians will describe the rise of the World Wide Web as the turning point of their academic profession. As a matter of fact, thanks to an unprecedented amount of digitization projects and to the preservation of born-digital sources, for the first time they have at their disposal a gigantic collection of traces of our past. However, to obtain useful insights from these very large amounts of data, historians will need more and more fine-grained techniques. For this reason, at the Data and Web Science Group, we focus on developing approaches that can sustain researchers moving from text exploration studies towards hypothesis-testing researches. These solutions benefit from the combination of entity linking and topic models, among other methods. Additionally, we also believe that historians who intend to employ computational methods as evidences for supporting a claim, have to use computational methods not anymore as black boxes but as a series of well known methodological approaches. For this reason, the second goal of our research group is to stress the importance of tool evaluation in digital history. In our talk, we will present an overview of some of the works we conducted so far, in collaboration with the Historical Institute and the Political Science Department of the University of Mannheim.

 

ALL WELCOME!

Announcement: Winner of the Göttingen Dialog in Digital Humanities (GDDH) award 2016

The board of the Göttingen Dialog in Digital Humanities is pleased to announce the three best contributions of this year’s GDDH series. The winner will be handed a prize of €500 and candidates in the second and third positions will receive a notable mention.

We are delighted to announce that the winner of the seminar series of 2016 is:

Hazel Wilkinson
from the University of Cambridge, United Kingdom

with
“A database of printers’ ornaments”

Screen Shot 2016-08-12 at 12.17.46
Hazel Wilkinson presenting at GDDH16 on June 27th

The prize is awarded on the basis of an evaluation of both the paper and the quality of the presentation, for which this candidate received 85.73/100!

The winner is followed by yet another worthy candidate with a paper entitled “Inferring standard name form, gender and nobility from historical texts using stable model semantics”. The paper, written by Davor Lauc and Darko Vitek and presented by Davor Lauc from the University of Zagreb in Croatia, receives a notable mention for its high standard and well-presented research results. This candidate received a score of 79.84/100.

The second notable mention is awarded to the paper “Experiments of distributional semantics in stylometry” by Giulia Benotto from the Institute of Computer Linguistics (CNR) in Pisa, Italy. This paper and presentation follows with a total score of 75.68/100. This candidate was appreciated for the originality of the topic and the clear explanation of the methodology.

The slides and videos of these talks are available here.

Evaluation Method

Continue reading

ADHO Award 2016

Just like the happy ending of a fairy tale: the Franzini sisters win an ADHO Bursary Award of 2016 for research on the Grimm brothers!

Once upon a time there were two sisters, Greta and Emily. The sisters lived in an old building called Heyne Haus in the small German town of Göttingen. As Digital Humanities elves they busied themselves to find something that would keep them occupied indoors during the cold winter of 2015. And like the Grimm brothers who lived in that very same town two hundred years before them, they started, together with a group of loyal companions, collecting stories and motifs. Fairy tale motifs to be precise…

The Digital Breadcrumbs of Brothers Grimm project, which began in October 2015, is collecting and automatically detecting folktale motifs as text reuse units or minimal primitives. In fact, with this project Emily, Greta and their colleagues (constituting the early career research group eTRAP) are addressing two specific challenges of their field: text reuse detection at scale and cross-lingual text reuse detection. While they’ve already experimented and have shown good results for the former (download the DH 2016 slides and poster from their website here, the latter challenge is still ongoing as they’re in the process of manually collecting the necessary data in order to train TRACER, a text reuse detection engine comprising 700 different algorithms, and other software, to detect motifs across multiple languages. For this challenge, they’ve selected three Grimm fairy tales to work with: Snow White, Puss in Boots and The Fisherman and his Wife. To push their research forward, the sisters and their team find and read as many versions of these tales as they can (original versions, not translations, both predating and following the Grimm collection), collect motifs therein and add them to a matrix that maps languages against one another. In the second stage of the project this multilingual dataset will be used by the software tools to automatically find other matches at web scale. Furthermore, the dataset will be integrated with existing ontological resources and will lead to an exploration of folktale motifs as Linked Open Data. With the Digital Breadcrumbs of Brothers Grimm project, Emily, Greta and their team are not only able to advance research in automatic text reuse detection, but can also support folklorists and literary scholars in tackling the large amount of folkloristic materials now available online.

For their ideas and work the Franzini sisters have been awarded the ADHO Bursary Award of 2016. The award is given to promising young scholars of the Digital Humanities who make a new valuable contribution to the field. The ceremony took place during this year’s Digital Humanities Conference in Kraków. Greta has been exploring this area of study since 2009 when she began a Master’s in Digital Humanities at King’s College London (KCL). She is now at the end of a PhD in Digital Humanities at University College London (UCLDH), while working as a Research Associate in the Institute of Computer Science at Göttingen University. Emily was introduced later to the field, when she was hired as a Researcher at the Humboldt Chair of Digital Humanities in Leipzig in 2013 and later began working as a Research Associate at the Institute of Computer Science in Göttingen.

Photo collage.

AIUCD 2016, Venice

Photo of a fingerprintWe’re very pleased to announce that eTRAP will be giving a text reuse tutorial at the annual conference of the Italian Association for Digital Humanities in Venice, Italy, this coming September! It’s the only tutorial of the conference and it will run on 6th and 7th September at the Ca’ Foscari University.

The tutorial builds on eTRAP’s research activities, most of which deploy Marco Büchler’s TRACER tool. TRACER is a suite of algorithms aimed at investigating text reuse in multifarious corpora, be those prose, poetry, in Italian or medieval German. TRACER provides researchers with statistical information about the texts under investigation and its integrated reuse visualiser, TRAViz, displays the reuses in a more readable format for further study.

This tutorial seeks to teach participants to independently understand, use and run TRACER. For the purpose of the tutorial and to ensure the smoothest possible outcome, participants will initially be working on data-sets provided by eTRAP. Depending on the overall progress, we may also allocate some time to investigating the participants’ own data-sets, provided these comply with the TRACER format1.

The workshop will be conducted in English. An Italian version of the tutorial flyer is available here. For more information about previous editions of this tutorial, visit our Events page.

Eligibility & Requirements

If you’re interested in exploring text reuse between two or multiple texts (in the same language) and would like to learn how to do it semi-automatically, then this tutorial is for you. In order to provide everyone with adequate (technical) assistance, the workshop can only accommodate 12 participants. To apply to the tutorial, please send your CV and a motivation letter to etrap-applications(at)gcdh(dot)de by July 31th, 2016. Those accepted will have to register for the AIUCD conference.

We look forward to seeing you in Venice!


1Should you be interested in investigating your own texts, please send us an email to the address above so that we can send you the requirements.

Article: Visual Text Analysis in Digital Humanities

Greta’s latest article “Visual Text Analysis in Digital Humanities“, co-authored with Stefan Jänicke, Muhammad Faisal Cheema and Gerik Scheuermann, has just been published by the Computer Graphics Forum! Here is the abstract:

In 2005, Franco Moretti introduced Distant Reading to analyze entire literary text collections. This was a rather revolutionary idea compared to the traditional Close Reading, which focuses on the thorough interpretation of an individual work. Both reading techniques are the prior means of Visual Text Analysis. We present an overview of the research conducted since 2005 on supporting text analysis tasks with close and distant reading visualizations in the digital humanities. Therefore, we classify the observed papers according to a taxonomy of text analysis tasks, categorize applied close and distant reading techniques to support the investigation of these tasks and illustrate approaches that combine both reading techniques in order to provide a multi-faceted view of the textual data. In addition, we take a look at the used text sources and at the typical data transformation steps required for the proposed visualizations. Finally, we summarize collaboration experiences when developing visualizations for close and distant reading, and we give an outlook on future challenges in that research area.

Feedback welcome!

Current open paid positions for Student Assistants

Two Transcribers wanted!

(Targeted at students of German Literature or other Humanities subjects)

The early career research group eTRAP is looking for Student Assistants. The research group is associated with the Institute of Computer Science and operates from the Göttingen Centre for Digital Humanities (GCDH). Further information about the research group and its work can be found at http://etrap.gcdh.de.

Job description
We are looking for applicants interested in joining the research group on TrAIN, a new project which was recently awarded the sum of €20,000 by the University of Göttingen. TrAIN, which stands for Tracing Authorship in Noise, will run for the duration of six months from 1st June 2016. The aim of the project is to obtain digital and searchable copies of the original correspondence of the Grimm brothers – the famous authors of the Kinder- und Hausmärchen. The digital copies will be obtained in two different ways, namely by the use of an HTR (Handwritten Text Recognition) tool and multiple OCR (Optical Character Recognition) tools. The output of such work will then be used to further research in the fields of stylometry and authorship attribution.
We are hiring 2 students for the duration of 3 months (extendable contract) who will act as the transcribers of the team. They will work with Transkribus, an HTR tool used to transcribe handwritten texts.

Continue reading