A new AI translation model which can interpret Yiddish handwriting with 95 per cent accuracy will "make the voices of the past eligible again".
The Vilne-Yiddish model, was developed by Dr Sergii Gurbych, a postdoctoral fellow at the Centre for the Study of East European Jewry Faculty of History at Vilnius University, Lithuania, and has been trained by being shown a series of Yiddish texts.
The new model will make the future of translation of texts far easier, with scholars currently having to manually translate difficult to read handwriting.
Gurbych said: “There are many different handwriting styles. They differ by period, region, and even by social background.
"Currently, scholars working with Yiddish texts manually transcribe dozens of pages from autobiographies, diaries, and letters - a process that is both time-consuming and labour-intensive.
AI will be able to do this in a fraction of the time.
"This will help historians and linguists analyse handwritten sources that were previously too complex to process automatically,” said Gurbych.
Dr Sergii Gurbych who developed the model (Image: Vilnius University)[Missing Credit]
Other similar models have been developed in the past, but the Vilne-Yiddish is open access, meaning users will be able to add to it and other AIs will be able to learn from it, exponentially improving the future of AI Yiddish translation.
Writings of the past, which once could only be read by a Yiddish speaker, will now be able to be simply copied and pasted into a translator, allowing Jewish communities who no longer speak Yiddish - and anyone else who wishes to - connect with their past.
Gurbych continued: “Ultimately, Digital Humanities isn’t just about digitisation or data analysis - it’s about expanding access to culture and making the voices of the past legible again.”
To get more news, click here to sign up for our free daily newsletter.
