All of Tolstoy in One Click is an international crowdsourcing project that unites technologies and social effort. It continues the current trend of preserving cultural heritage –– for global audiences and inspires a number of other similar projects.
Tolstoy: famous and rare
It’s hard to find a literature fan anywhere in the world who hasn’t heard of writer Leo Tolstoy who lived in Russia in later 19th century. War and Peace is one of his most famous sagas which became synonymous to a long literary work with many characters and lines. There are more films around the world based on Tolstoy’s book Anna Karenina than on any other book ever. Unbelievable as it may be, the full works of Tolstoy are available to a very limited audience, being kept in private collections and libraries. The full 90 volumes of Tolstoy literary works have been published only once with an edition of a mere 5,000 units and never republished.
Apart from the finished works of fiction - prose, poetry, drama - these volumes contain numerous drafts, manuscripts and drawings, all sorts of editorial comments, rare stories, novels, diaries, letters, religious tracts, philosophical thesis, travelogues, childhood memories, essays and schoolbooks.
However, by the turn of the 21st century, the great writer’s works were turning into a bibliographic rarity. Unless preserved, it would have been a huge loss not only to millions of the writer's admirers, but also for universities, historians, and modern writers.
How Tolstoy fans used technologies
When Leo Tolstoy State Museum in Moscow, Russia, decided to digitize complete works of Tolstoy, they turned to ABBYY, aware of the company’s similar projects with European universities and libraries. The company’s text recognition technologies have already been successfully used to digitize works for Project Gutenberg digital library, IMPACT, METAe and Southampton University library to name a few.
The second part of the project involved verification, to ensure that the software has correctly recognized and digitized all the information. An ordinary project would have involved professional correctors and verifiers. However, All-of-Tolstoy in one click was no ordinary project. It was a mission to make the great writer’s work available to the masses. ABBYY and Fyokla Tolstaya, Leo Tolstoy’s great-great-granddaughter, and the author of the project, jointly decided to call in volunteers. “It was so much in the spirit of Tolstoy to gather people of all walks of life to help a common project and allow fans see rare materials first hand,” – said Fyokla Tolstaya.
As a result, the Tolstoy project turned into a massive crowdsourcing effort, attracting more than 3,000 volunteers from 49 countries around the world.
Each volunteer got a special license for ABBYY FineReader and a package of 20 pages of Tolstoy’s works in PDF image files. The AI job was OCR or optical character recognition – to automatically recognize text on images and make it searchable, while volunteers were in charge of the final verification. The job of volunteers was not easy as they had to proofread not only Russian text – sometimes in old Cyrillic – but also French, Greek, Latin and other languages as Tolstoy wrote his works in many languages. FineReader supports 192 languages and could easily digitize all of Tolstoy works, some of which were written in different languages. The software detects and highlights potential mistakes easing the entire proofreading process for volunteers.
The work of volunteers was organized through a dedicated website – readingtolstoy.ru – which now hosts a map with volunteers’ locations, press materials about the projects and other related information.
As a result, the entire 46,820 pages and 14.5 million words were recognized and proofread within 14 days at the rate of 8.5 book volumes per day.
From archive digitization to a trendsetting project
Once all 90 volumes went online, ABBYY specialists joined efforts with tablet-maker Wexler to create 761 electronic books: one for each volume and for each piece of work. Now all of them are accessible at www.tolstoy.ru, the official Internet portal dedicated to the writer’s life and writings, developed by the Tolstoy Museum and the Tolstoy’s Estate-Museum in Yasnaya Polyana.
The All Tolstoy in One Click project has become a trendsetter for a number of other projects. Currently in progress are: the Tolstoy language dictionary, semantic text search across selected stories, and the 100-volume set of writer's works – a 20-year project by the Institute of World Literature of Russian Academy of Sciences. The Bolshoi Theatre is digitizing its programs and playbills.
According to Fyokla Tolstaya, the writer's last will was to make his works available to everyone free of charge. This way, All Tolstoy in One Click project was not only a fine example of how technology and art can come together, but also a fulfilment of the writer's dream of living a useful life for others.
By Daria Kertsenbaum
Subscribe for blog updates
Your subscription was successful! Kindly check your mailbox and confirm your subscription. If you don't see the email within a few minutes, check the spam/junk folder.
Your subscription was successful!
Kindly check your mailbox and confirm your subscription. If you don't see the email within a few minutes, check the spam/junk folder.