This article demonstrates the benefits and pitfalls of utilizing Natural Language Processing to structure a large corpus of newspaper adverts on fugitive enslaved people from the Atlantic World between 1766 and 1821. We evaluate a model for multilingual event extraction trained specifically for fugitive ads and jail lists in its capacity to extract correctly the attributes relevant for historical analysis. Finally, we discuss how the current model may be used to expand and qualify databases concerning enslaved fugitives in the eastern Caribbean.
The paper describes the Corpus of Wangerooge Frisian (CWF), an online resource gathering the extant documentation of the East Frisian variety formerly spoken on the island of Wangerooge. In addition to the, textual material, the corpus includes recently made transcriptions of about half an hour of audio recordings from...
Prompted by the publication of a new bilingual edition (with notes) of the first and second declamations in the
Corpus Libanianum
, this note presents some thoughts on these texts. While acknowledging the general usefulness of the new edition, it points out some shortcomings regarding the historical context of th...
Abstract:This article presents the background to, and a description of, a newly developed online database of historical and contemporary lexical data for languages of the region on and around the Bird's Head of New Guinea. In the first public release described here, the OUTOFPAPUA database collects more than 200,000 le...
Antoinette Schapper, David Kamholz· Oceanic Linguistics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
