Temporal classification for historical Romanian texts
Alina Maria Ciobanu, Anca Daniela Dinu, Liviu P. Dinu, Vlad Niculae, Octavia-Maria Şulea · 2013
In this paper we look at a task at border of natural language processing, historical linguistics and the study of language de-velopment, namely that of identifying the time when a text was written. We use machine learning classification using lexi-cal, word ending and dictionary-based fea-tures, with linear support vector machines and random forests. We find that lexical features are the most helpful. 1