The Lib2Life Platform – Processing, Indexing and Semantic Search for Old Romanian Documents

Abstract

Preserving the cultural heritage of a nation throughout generations is essential in a continuously developing society. This paper introduces the Lib2Life platform powered by advanced Natural Language Processing techniques, focusing on the processing, indexing and semantic search of old documents from the Central University Libraries in Romania. Our platform enables the upload and text preprocessing of scanned documents by librarians, who can afterwards manually correct the extracted content and corresponding metadata. In addition, Lib2Life ensures the exploration of the collection of books using a semantic search engine to retrieve documents fitted to the users' interests. The platform was evaluated using an usability questionnaire which pinpointed out that Lib2Life is a modern and user-friendly smart search engine for old documents written in the Romanian language. Improvements in terms of server response time and functionality were suggested. The platform proved to be intuitive and easy to use, having the potential to become an analytical system incorporating a rich and diverse collection of books.