Technology

The Arolsen Archives’ #everynamecounts project uses artificial intelligence to uncover information about victims of National Socialist persecution

A team of Accenture (NYSE: ACN) volunteers has developed an artificial intelligence (AI)-based solution that helps extract information about victims of Nazi persecution from documents in the Arolsen Archives 40 times faster than before.

The Arolsen Archives preserve the world’s largest collection of documents related to Nazi persecution – 110 million documents and digital objects, some of which are part of the UNESCO “Memory of the World” program – to keep alive the memory of the crimes of the German terror regime to keep. A key part of the archival work is making these documents accessible to anyone wanting to search for traces of Holocaust victims and survivors, persecution of minorities, and forced labor.

Each document kept in the archives must be checked and its information (e.g. family name and date of birth on a prisoner registration form) entered into a database. To facilitate this process, the Arolsen Archives created “#everynamecounts”, a crowdsourcing project for volunteers to manually extract information from documents.

Manually translating, reading, transcribing, cataloging, and validating these documents can take decades. Each document is indexed independently by three volunteers and, if there are any discrepancies, checked for accuracy by an Arolsen Archives employee. In fact, up to four people can index and validate four documents in an hour.

Ian Lever, an Accenture volunteer and member of the company’s Jewish Employee Resource Group, quickly realized that AI could significantly speed up this process. Within 10 weeks, he and other Accenture volunteers set up an AI solution to index the documents. With AI gathering information faster and increasing its accuracy, four volunteers can now validate approximately 160 documents in an hour, a 40x increase in productivity.

Working with Accenture’s Solutions.AI team, the volunteers configured an existing Accenture AI solution that leverages optical character recognition and machine learning. It indexes documents that are particularly difficult and tedious for humans to extract. Including prisoner and transfer lists with dozens of lines, concentration camp records and search documents, i.e. investigations into the whereabouts and fates of family members and relatives.

Even with the AI ​​doing the heavy lifting, human oversight of the process remains important, not only to ensure accuracy, but also to let the AI ​​solution learn. By reviewing and correcting information, volunteers “teach” the solution to recognize period-typical handwritten characters and abbreviations. Thanks to her input, the AI ​​gradually improved her accuracy by 10% within the Mother’s Last Name form field. For the “Religion” section, the AI ​​now works with a confidence level of 99%.

Since Accenture implemented the AI ​​solution in December 2021, the solution has indexed more than 160,000 names of victims of Nazi persecution, extracted information from more than 18,000 documents, and grouped more than 60,000 documents into similar groups for identification and analysis to enhance.

More than 950 Accenture employees have volunteered for the project so far, with Accenture also supporting the maintenance and further development of the AI ​​solution.

“We are proud of our people’s efforts to keep alive the memory of those who have endured unimaginable pain and suffering at a time when anti-Semitism, racism and ultra-nationalism are rearing their ugly heads again,” he said David Metnick, executive director and lead sponsor of the project at Accenture. “We saw a problem and in it an opportunity to live our values ​​and use digital technologies for good.”

“We are overwhelmed by how many volunteers support the digitization of our archive,” says Floriane Azoulay, Director of the Arolsen Archives. “Our collaboration with the Accenture team is outstanding. It’s great that there is now a digital solution to capture the content of documents faster, which helps ensure that more important information about the fates of victims of Nazi persecution can be found in our online archive.”

Learn more about how Accenture volunteers contributed to #everynamecounts.

https://techround.co.uk/news/arolsen-archives-everynamecounts-project-uses-artificial-intelligence/?utm_source=rss&utm_medium=rss&utm_campaign=arolsen-archives-everynamecounts-project-uses-artificial-intelligence The Arolsen Archives’ #everynamecounts project uses artificial intelligence to uncover information about victims of National Socialist persecution

Fry Electronics Team

Fry Electronics.com is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – admin@fry-electronics.com. The content will be deleted within 24 hours.

Related Articles

Back to top button