Skip to main content

Making Holocaust Oral Testimonies More Usable as Research Data

, - ,

General Details  

Date: 15-17 May 2023
Time: all day
Venue: King's College London

About

The European Holocaust Research Infrastructure (EHRI) and the Common Language Resources and Technology Infrastructure (CLARIN) are combining their expertise to explore Oral Testimonies of the Holocaust in a Hackathon to be held at King’s College London. 

‘Making Holocaust Oral Testimonies more usable as Research Data’ will be a practical, hands-on event where curators of oral history recordings, Holocaust researchers, digital humanists and language technologists will get together to work on making oral testimony recordings more usable as research data. This workshop will work on a small number of Holocaust testimony recordings, with an aim to establish a usable and reproducible workflow and toolchain to progress from digital recordings to transcribed and annotated datasets. The workshop will also focus on the challenges of dealing with geodata from Holocaust testimonies.

The workshop will conclude on Wednesday with a strategic session to explore continued future cooperation between the EHRI and CLARIN infrastructures.

The languages covered will include English, German, Italian, Czech, Polish and Slovak.


Topics

The workshop will take place over three days, with a series of hands-on sessions where members of both the EHRI and CLARIN infrastructures will work with workshop participants to concentrate on issues centred around the following areas and the specifics of their application in the field of the Holocaust Studies:

  • Cleaning data
  • Time alignment
  • Language identification
  • Lemmatization
  • Automatic keyword extraction
  • Metadata extraction
  • Normalisation of non-standard features
  • Automatic speech recognition
  • Overlapping speech
  • Translation
  • Named entity recognition
  • Summarization
  • Word-class (part of speech) annotation
  • Parallel alignment of non-standard features
  • Making text transcription more searchable and usable

 

Dissemination

 
For more information about the event, please read the detailed blog 'Using Holocaust Testimonies as Research Data. Resources for Researchers' by Martin Wynne.