Transforming Archived Resources with Language Technology: From Manuscripts to Language Documentation

Transcriptions in different languages are a ubiquitous data format in linguistics and in many other fields in the humanities. However, the majority of these resources remain both under-used and under-studied. This may be the case even when the materials have been published in print, but is certainly the case for the majority of unpublished transcriptions. Our paper presents a workflow adapted in the research project Language Documentation Meets Language Technology, which combines text recognition, automatic transliteration and forced alignment into a process which allows us to convert earlier transcribed documents to a structure that is comparable with contemporary language documentation corpora. This has complex practical and methodological considerations.