@inproceedings{liimatta-2023-effect,
title = "Effect of data quality on the automated identification of register features in Eighteenth Century Collections Online",
author = "Liimatta, Aatu",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Pirinen, Flammie and
Alnajjar, Khalid and
Miyagawa, So and
Bizzoni, Yuri and
Partanen, Niko and
Rueter, Jack},
booktitle = "Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages",
month = dec,
year = "2023",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlp4dh-1.6",
pages = "45--51",
abstract = "Many large-scale investigations of textual data are based on the automated identification of various linguistic features. However, if the textual data is of lower quality, automated identification of linguistic features, particularly more complex ones, can be severely hampered.Data quality problems are particularly prominent with large datasets of historical text which have been made machine-readable using optical character recognition (OCR) technology, but it is unclear how much the identification of individual linguistic features is affected by the dirty OCR, and how features of varying complexity are influenced differently.In this paper, I analyze the effect of OCR quality on the automated identification of the set of linguistic features commonly used for multi-dimensional register analysis (MDA) by comparing their observed frequencies in the OCR-processed Eighteenth Century Collections Online (ECCO) and a clean baseline (ECCO-TCP). The results show that the identification of most features is disturbed more as the OCR quality decreases, but different features start degrading at different OCR quality levels and do so at different rates.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liimatta-2023-effect">
<titleInfo>
<title>Effect of data quality on the automated identification of register features in Eighteenth Century Collections Online</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aatu</namePart>
<namePart type="family">Liimatta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many large-scale investigations of textual data are based on the automated identification of various linguistic features. However, if the textual data is of lower quality, automated identification of linguistic features, particularly more complex ones, can be severely hampered.Data quality problems are particularly prominent with large datasets of historical text which have been made machine-readable using optical character recognition (OCR) technology, but it is unclear how much the identification of individual linguistic features is affected by the dirty OCR, and how features of varying complexity are influenced differently.In this paper, I analyze the effect of OCR quality on the automated identification of the set of linguistic features commonly used for multi-dimensional register analysis (MDA) by comparing their observed frequencies in the OCR-processed Eighteenth Century Collections Online (ECCO) and a clean baseline (ECCO-TCP). The results show that the identification of most features is disturbed more as the OCR quality decreases, but different features start degrading at different OCR quality levels and do so at different rates.</abstract>
<identifier type="citekey">liimatta-2023-effect</identifier>
<location>
<url>https://aclanthology.org/2023.nlp4dh-1.6</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>45</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effect of data quality on the automated identification of register features in Eighteenth Century Collections Online
%A Liimatta, Aatu
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Pirinen, Flammie
%Y Alnajjar, Khalid
%Y Miyagawa, So
%Y Bizzoni, Yuri
%Y Partanen, Niko
%Y Rueter, Jack
%S Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages
%D 2023
%8 December
%I Association for Computational Linguistics
%C Tokyo, Japan
%F liimatta-2023-effect
%X Many large-scale investigations of textual data are based on the automated identification of various linguistic features. However, if the textual data is of lower quality, automated identification of linguistic features, particularly more complex ones, can be severely hampered.Data quality problems are particularly prominent with large datasets of historical text which have been made machine-readable using optical character recognition (OCR) technology, but it is unclear how much the identification of individual linguistic features is affected by the dirty OCR, and how features of varying complexity are influenced differently.In this paper, I analyze the effect of OCR quality on the automated identification of the set of linguistic features commonly used for multi-dimensional register analysis (MDA) by comparing their observed frequencies in the OCR-processed Eighteenth Century Collections Online (ECCO) and a clean baseline (ECCO-TCP). The results show that the identification of most features is disturbed more as the OCR quality decreases, but different features start degrading at different OCR quality levels and do so at different rates.
%U https://aclanthology.org/2023.nlp4dh-1.6
%P 45-51
Markdown (Informal)
[Effect of data quality on the automated identification of register features in Eighteenth Century Collections Online](https://aclanthology.org/2023.nlp4dh-1.6) (Liimatta, NLP4DH-IWCLUL 2023)
ACL