Nicholas Woodward, Software Developer at the University of Texas Libraries, shares the text of the talk he gave at the Texas Conference on Digital Libraries. Woodward describes his novel approach for transcribing the Digital Archive of the Guatemalan National Police Historical Archive, a collection of over 12 million pages:

My approach looks to break up documents into individual words with the idea that though no two documents are exactly alike they are likely to contain similar words. And across an entire corpus, particularly very large ones such as AHPN, words are likely to appear many times. Consequently, if users transcribe the words of one document, then I can use image matching algorithms to find other images of the same words and apply the crowdsourced transcription to the new images.

The University of Nebraska-Lincoln has unveiled the first project in its effort to transcribe digitized documents through crowd-sourcing. UNL “alumni, students, and friends” are invited to volunteer to transcribe the collection of UNL’s historical Cornhusker yearbooks. The transcription project arose through a collaboration between the Archives & Special Collections, the Center for Digital Research in the Humanities (CDRH), Computer Operations and Research Services, and Development and Outreach at UNL.

The site for yearbook transcription, which extends the Transcribr Drupal distribution, marks progress for the overall project as well as individual yearbooks.

A complete run of the yearbooks is currently available online (but not yet full-text searchable… pending transcription!).