An approach to named entity extraction from historical documents in traditional Mongolian script

Abstract

In this poster, we propose an information extraction method for digitized ancient Mongolian documents by utilizing an ancient-modern dictionary. Named entities such as historical figures and place names will be extracted by employing text mining techniques that aim to reduce the labor-intensive annotation on historical text. The Text Encoding Initiative (TEI) guidelines will be applied to digital text representations that encode the historical figures and place names along with their interpretations, and commentaries.