@inproceedings{rastas-etal-2022-explainable,
title = "Explainable Publication Year Prediction of Eighteenth Century Texts with the {BERT} Model",
author = {Rastas, Iiro and
Ciar{\'a}n Ryan, Yann and
Tiihonen, Iiro and
Qaraei, Mohammadreza and
Repo, Liina and
Babbar, Rohit and
M{\"a}kel{\"a}, Eetu and
Tolonen, Mikko and
Ginter, Filip},
editor = "Tahmasebi, Nina and
Montariol, Syrielle and
Kutuzov, Andrey and
Hengchen, Simon and
Dubossarsky, Haim and
Borin, Lars",
booktitle = "Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.lchange-1.7",
doi = "10.18653/v1/2022.lchange-1.7",
pages = "68--77",
abstract = "In this paper, we describe a BERT model trained on the Eighteenth Century Collections Online (ECCO) dataset of digitized documents. The ECCO dataset poses unique modelling challenges due to the presence of Optical Character Recognition (OCR) artifacts. We establish the performance of the BERT model on a publication year prediction task against linear baseline models and human judgement, finding the BERT model to be superior to both and able to date the works, on average, with less than 7 years absolute error. We also explore how language change over time affects the model by analyzing the features the model uses for publication year predictions as given by the Integrated Gradients model explanation method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rastas-etal-2022-explainable">
<titleInfo>
<title>Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iiro</namePart>
<namePart type="family">Rastas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yann</namePart>
<namePart type="family">Ciarán Ryan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iiro</namePart>
<namePart type="family">Tiihonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammadreza</namePart>
<namePart type="family">Qaraei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liina</namePart>
<namePart type="family">Repo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Babbar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eetu</namePart>
<namePart type="family">Mäkelä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Tolonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Ginter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Tahmasebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Kutuzov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hengchen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haim</namePart>
<namePart type="family">Dubossarsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Borin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe a BERT model trained on the Eighteenth Century Collections Online (ECCO) dataset of digitized documents. The ECCO dataset poses unique modelling challenges due to the presence of Optical Character Recognition (OCR) artifacts. We establish the performance of the BERT model on a publication year prediction task against linear baseline models and human judgement, finding the BERT model to be superior to both and able to date the works, on average, with less than 7 years absolute error. We also explore how language change over time affects the model by analyzing the features the model uses for publication year predictions as given by the Integrated Gradients model explanation method.</abstract>
<identifier type="citekey">rastas-etal-2022-explainable</identifier>
<identifier type="doi">10.18653/v1/2022.lchange-1.7</identifier>
<location>
<url>https://aclanthology.org/2022.lchange-1.7</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>68</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model
%A Rastas, Iiro
%A Ciarán Ryan, Yann
%A Tiihonen, Iiro
%A Qaraei, Mohammadreza
%A Repo, Liina
%A Babbar, Rohit
%A Mäkelä, Eetu
%A Tolonen, Mikko
%A Ginter, Filip
%Y Tahmasebi, Nina
%Y Montariol, Syrielle
%Y Kutuzov, Andrey
%Y Hengchen, Simon
%Y Dubossarsky, Haim
%Y Borin, Lars
%S Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F rastas-etal-2022-explainable
%X In this paper, we describe a BERT model trained on the Eighteenth Century Collections Online (ECCO) dataset of digitized documents. The ECCO dataset poses unique modelling challenges due to the presence of Optical Character Recognition (OCR) artifacts. We establish the performance of the BERT model on a publication year prediction task against linear baseline models and human judgement, finding the BERT model to be superior to both and able to date the works, on average, with less than 7 years absolute error. We also explore how language change over time affects the model by analyzing the features the model uses for publication year predictions as given by the Integrated Gradients model explanation method.
%R 10.18653/v1/2022.lchange-1.7
%U https://aclanthology.org/2022.lchange-1.7
%U https://doi.org/10.18653/v1/2022.lchange-1.7
%P 68-77
Markdown (Informal)
[Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model](https://aclanthology.org/2022.lchange-1.7) (Rastas et al., LChange 2022)
ACL
- Iiro Rastas, Yann Ciarán Ryan, Iiro Tiihonen, Mohammadreza Qaraei, Liina Repo, Rohit Babbar, Eetu Mäkelä, Mikko Tolonen, and Filip Ginter. 2022. Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model. In Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change, pages 68–77, Dublin, Ireland. Association for Computational Linguistics.