Named Entity Recognition with Conditional Random Fields on Turkish News Dataset: Revisiting the Features

Abstract

Named entity recognition is a natural language processing problem that aims to mark entity names, such as person, place, organization, date, time, money and percentage, from different types of text. Various applications such as location estimation, event time estimation, determination of important people in the text can be possible with the solutions to this problem. The number of named entity recognition studies on Turkish texts is quite limited compared to those on English. In this study, the use of the technique Conditional Random Fields for the named entity recognition in Turkish news texts has been reviewed and the effect of new attributes on the model accuracy has been analyzed. The results of the experiments on different data sets are compared with the similar studies and presented.