This is the repository for our paper "Survey and reproduction of computational approaches to dating of historical texts", published at NoDaLiDa 2021.
Finding the year of writing for a historical text is of crucial importance to historical and philological research. However, the year of original creation is rarely explicitly stated and must be inferred from the text content, historical records, and codicological clues. Given a transcribed text, machine learning has successfully been used to estimate years of production. In this paper, we present an overview of estimation approaches from the literature for historical text archives, spanning from the 12th century until today.
@inproceedings{boldsen-wahlberg-2021-survey,
title = "Survey and reproduction of computational approaches to dating of historical texts",
author = {Boldsen, Sidsel and
Wahlberg, Fredrik},
booktitle = "Proceedings of the 23nd Nordic Conference on Computational Linguistics",
year = "2021",
address = " Reykjavik, Iceland",
abstract = "Finding the year of writing for a historical text is of crucial importance to historical and philological research. However, the year of original creation is rarely explicitly stated and must be inferred from the text content, historical records, and codicological clues. Given a transcribed text, machine learning has successfully been used to estimate years of production. In this paper, we present an overview of estimation approaches from the literature for historical text archives, spanning from the 12th century until today.",
}Dept. of Nordic Studies and Linguistics
University of Copenhagen
Dept. of Linguistics and Philology
Uppsala University