In the Yandex “Find in Archives” service you can decipher records with complex pre-revolutionary spelling. More than 2.5 million pages of historical documents with text transcriptions are in the public domain. The service copes with decryption in a couple of seconds. This was reported to RB.RU in the press service of the company.
The new algorithm, built on the basis of an optical character recognition system, takes into account the characteristics of handwriting, recognizes letters that have lost their relevance and understands the special structure of archival documents.
The first fund presented on the service was the Moscow Main Archive: it was on its materials that the developers trained the neural network. Now the database has been replenished with documents from the archives of the Orenburg and Novgorod regions. Over time, the number of available scan archives and archives will increase.
“Archival search” will increase the efficiency of the work of historians, sociologists, demographers, genealogists, and will help those who are looking for information about their family.
Among the documents are parish registers, confession sheets, revision tales with the results of the 18th – early 20th century population census.
Recordings can be found in the catalog or via the search bar. There are filters by years, files, funds and inventories. Next to each page scan is a line-by-line decoding performed by Yandex neural networks. If you hover over the desired fragment, it will immediately be highlighted on the digital copy.
Author:
karina pardaeva
Source: RB
I am Bret Jackson, a professional journalist and author for Gadget Onus, where I specialize in writing about the gaming industry. With over 6 years of experience in my field, I have built up an extensive portfolio that ranges from reviews to interviews with top figures within the industry. My work has been featured on various news sites, providing readers with insightful analysis regarding the current state of gaming culture.
