An Approach to Named Entity Extraction from Mongolian Historical Documents

In this poster, we demonstrate a named entity extraction method for digitized ancient Mongolian documents by using the features of characters´ appearance in a word. Named entities such as personal names and place names will be extracted by employing Support Vector Machine that aims to reduce the labor-intensive analysis on historical text. The preliminary results of our experiment show that the proposed method has gained 0.6993, 0.5679 and 0.6268 of precision, recall and F-measure, respectively.