Essert, Mario and Štrkalj Despot, Kristina and Lončarić, Mario and Štimac, Božidar (2013) DocMark & TEIMark - New visual WEB annotation tools for images & documents. = DocMark & TEIMark - New visual WEB annotation tools for images & documents. In: CroArtScia2013 – Asymmetry: Art & Science & Education, 08-11.05.2013., Zagreb, Hrvatska.
Full text not available from this repository.Abstract
Croatian institutions are in a possession of a large corpus of digitalized cultural heritage, which is sometimes stored in archives and accessible only to professionals, and sometimes it is publically available on the Internet. The DocMark program was built with the aim of tag digitalized image documents so that those tags may be analyzed and/or compared in each document. After the DocMark was built, it took three years to build TEIMark – text marking program which recognizes typed, transcribed or automatically recognized texts. While in DocMark tagging is performed on the image document (in which material characteristics are interesting and reachable unlike the content), in TEIMark tagging is performed on the real text, and not its image. This enables research focused on the content of the document such as linguistic research (here we will give an example of metaphor tagging) and other content focused research.
| Item Type: | Conference or Workshop Item (Lecture) |
|---|---|
| Keywords (Croatian): | DocMark, TEIMark, annotation, tagging |
| Subjects: | Humanities > Philology |
| Divisions: | 900 Department of Robotics and Production System Automation > 910 Chair of Engineering Automation |
| Indexed in Web of Science: | No |
| Indexed in Current Contents: | No |
| Date Deposited: | 20 Sep 2016 07:10 |
| Last Modified: | 24 Sep 2018 10:57 |
| URI: | http://repozitorij.fsb.hr/id/eprint/6431 |
Actions (login required)
 |
View Item |
Citations:
Citations: