OCR for Foreign Language Scholarship

Awardee: Curtis Dozier

Semester of Award: Spring 2016

Materials Awarded: 1 copy of ABBYY Finereader Optical Character Recognition Software

Project Description:

Like many fields in the humanities, Classical scholars write in a wide range of languages, primarily English, German, Italian, French, and increasingly, Spanish. It is difficult to maintain a sufficient knowledge of all these languages to assess new scholarship quickly. Finereader, the best multi-lingual OCR software available, allows me to scan articles in a wide range of languages and then use automatic online translators to determine the basic outlines of their argument and methods. These translations are not sufficient to engage with this scholarship, only to evaluate whether I should take the time to work through each piece more carefully. The OCR’ed scans are also searchable for key terms, references to classical texts, or bibliography.

The software works as expected but the process takes more time than I had hoped. It takes time to scan the scholarship, including making sure the original copy is of sufficient quality for the software to work well, and then the scanned results require some interpretation and organization before they can be machine translated. Research assistants have been able to help me with some of this, with training. When I have obtained a clean scan and OCR’ed text I have found it extremely useful for the purposes described above.

 

This entry was posted in 2015-2016. Bookmark the permalink.