.png)
.png)
ENG
Searching through historical documents is becoming a thing of the past—literally. Paměť novin is revolutionizing historical text retrieval using semantic analysis and artificial intelligence. Forget about exact phrasing and struggling with OCR errors; this innovative tool understands your query in natural language and serves up relevant articles in seconds. Just enter your search and dive into authentic reports from the past.
Anyone who has ever searched through historical documents knows that finding information in digital libraries is often a long, uphill battle. Traditional full-text search methods hit their limits—they require precise input, ignore contextual meaning, and are dependent on the quality of OCR. The result? Hours of manual browsing with uncertain outcomes.
Paměť novin solves this problem. Thanks to semantic search and artificial intelligence it can understand the meaning of your query and find related articles, even if they don't contain an exact word match.
Digital libraries provide access to a vast amount of historical documents—newspapers, manuscripts, books, archival materials, maps, and sheet music. The Czech standard is the Kramerius system, which has been helping with the search, viewing, and management of digitized content for over 20 years. Moreover, it is one of our key projects that we have been working on for a long time.
Kramerius is based on simple searching and browsing of digitized content, where the user has the option to view the scan of the analog document, metadata, and the text layer known as OCR (Optical Character Recognition).
Searching in Kramerius first displays matching titles by name, author, or keywords, followed by full-text results found directly on individual pages throughout the archive. A panel with various filters is also available to further refine your results.
However, full-text search requires using the exact words found on the pages you are searching for, which can be difficult in some cases.
Paměť novin brings a new approach to searching digitized content. At Trinera, we designed this tool because we were aware of the limitations of traditional search in digital libraries. Based on our many years of working with Kramerius and feedback from researchers, we wanted to create a solution that enables more efficient and intuitive work with historical data.
Instead of relying on exact word matches, Paměť novin uses AI-based semantic search that understands the meaning of your query and finds related content accordingly.
Paměť novin can handle errors in OCR transcripts, archaic expressions, and historical terminology – it searches by meaning, not just literally.
Paměť novin currently contains 340,000 pages from 16 historical periodicals from the years 1893–1913. These include, for example,
This scope allows users to track contemporary reactions to historical events, analyze language development, and gain unique context for their research. We plan to expand this content further in the future.
While testing Newspaper Memory, we chose an interesting topic concerning a popular stereotype – complaints from older generations about the youth.
Complaints about "today's youth" are nothing new. We often hear that young people are spoiled compared to the past. But is today's young generation really worse than previous ones, or have older generations always complained about the young? We can easily verify this thesis. Newspaper Memory allows you to search through historical texts and find out whether similar criticisms appeared in newspapers over a hundred years ago – and what they looked like back then.
We entered the query: "Did people complain about the youth?"
These findings show that complaints about the youth are timeless. Older generations often perceive changes as a decline, while younger ones naturally accept and adapt to them. What some consider a breakdown of values, others perceive as progress – and this feeling of decline often stems from the fact that ways of life, customs, and technologies that shape daily reality are changing. At the same time, older people do not realize that they were once the target of the same criticisms. In reality, the youth do not fundamentally change – it is rather the environment and the tools they use that change.
Newspaper Memory reveals this eternal clash, helps you understand the social norms of the time and makes it possible to verify historical stereotypes directly in primary sources.
“As a librarian, I’ve spent hundreds of hours researching in digital libraries and often hit the limits of full-text search. I knew the information I needed was out there, but finding it was often demotivating and time-consuming. Sometimes I would have had to go through entire newspapers page by page, which just wasn’t feasible. If I’d had a tool like Paměť novin back then, I would have saved a huge amount of time—and a lot of frustration. 🙂”
Paměť novin is currently a prototypethat we are still improving. Want to get involved? Try the app at www.pametnovin.cz and give us your feedback!
Do you have an idea for how we could expand this tool? Would you like a similar search feature for your own institution and data? Get in touch with us and we can discuss it with no strings attached!
We will contact you within 2 business days.
