Open AccessArchive Card Index vs. Transkribus: machine recognition of handwritten text
Author(s) -
Oksana Tyshchenko
Publication year - 2021
Publication title -
sinopsis: tekst, kontekst, medìa
Language(s) - English
Resource type - Journals
ISSN - 2311-259X
DOI - 10.28925/2311-259x.2021.3.9
Subject(s) - computer science , index (typography) , ukrainian , context (archaeology) , natural language processing , artificial intelligence , relevance (law) , information retrieval , world wide web , linguistics , paleontology , philosophy , political science , law , biology
The subject of the research is machine recognition of handwritten materials of the Archival Card Index (ACI) — lexical and phraseological materials of the dictionary commission of the All-Ukrainian Academy of Sciences, in particular, card index of the “Russian-Ukrainian dictionary” 1924–1933 ed. A. Krymsky and S. Yefremov. The study of the ACI should be considered in the context of cultural and national revival in Ukraine in the 20th — early 21st centuries. The relevance and value of the ACI became a prerequisite for the transfer of its materials to the digital format. In 2018 the Institute of Ukrainian Language of the NAS of Ukraine created a computer system “Archival Card Index”, which accessibles materials primarily in the form of scanned images. The problem that needs urgent resolution is the transfer of handwriting to a typewriter format. The complexity of manual recognition, which requires considerable effort and time, encourages the study and application of Transkribus resource capabilities, which involves the use of the machine teaching. The Aim of the study is to clarify by analyzing, systematizing, classifying and describing the material features of the preparation of ACI cards for machine processing of texts. The scientific novelty of the study is that for the first time, the issue of providing the HTR engine with ACI training data (loading to the platform, segmenting images into lines and text areas, transcribing content each page).The main result is finding out the content of the preparatory stage, the tasks of which are to eliminate the flaws of automatic segmentation: non-text elements, non-substantial text elements, incorrect automatic detection of text region or line. The prospects of lexicographic toloka (crowdsourcing) in the process of card recognition are outlined, for which it is envisaged to use collective access to the collection of transcribed documents in Transkribus. To recognize the cards manually and for the future check and adjustment of automatically recognized ones, you can join the new project “All-Ukrainian Toloka: Archival Card Index” — online platform on the website “ACI”.