@inproceedings{bollmann-2019-large,
title = "A Large-Scale Comparison of Historical Text Normalization Systems",
author = "Bollmann, Marcel",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1389",
doi = "10.18653/v1/N19-1389",
pages = "3885--3898",
abstract = "There is no consensus on the state-of-the-art approach to historical text normalization. Many techniques have been proposed, including rule-based methods, distance metrics, character-based statistical machine translation, and neural encoder{--}decoder models, but studies have used different datasets, different evaluation methods, and have come to different conclusions. This paper presents the largest study of historical text normalization done so far. We critically survey the existing literature and report experiments on eight languages, comparing systems spanning all categories of proposed normalization techniques, analysing the effect of training data quantity, and using different evaluation methods. The datasets and scripts are made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bollmann-2019-large">
<titleInfo>
<title>A Large-Scale Comparison of Historical Text Normalization Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">Bollmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is no consensus on the state-of-the-art approach to historical text normalization. Many techniques have been proposed, including rule-based methods, distance metrics, character-based statistical machine translation, and neural encoder–decoder models, but studies have used different datasets, different evaluation methods, and have come to different conclusions. This paper presents the largest study of historical text normalization done so far. We critically survey the existing literature and report experiments on eight languages, comparing systems spanning all categories of proposed normalization techniques, analysing the effect of training data quantity, and using different evaluation methods. The datasets and scripts are made publicly available.</abstract>
<identifier type="citekey">bollmann-2019-large</identifier>
<identifier type="doi">10.18653/v1/N19-1389</identifier>
<location>
<url>https://aclanthology.org/N19-1389</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>3885</start>
<end>3898</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale Comparison of Historical Text Normalization Systems
%A Bollmann, Marcel
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F bollmann-2019-large
%X There is no consensus on the state-of-the-art approach to historical text normalization. Many techniques have been proposed, including rule-based methods, distance metrics, character-based statistical machine translation, and neural encoder–decoder models, but studies have used different datasets, different evaluation methods, and have come to different conclusions. This paper presents the largest study of historical text normalization done so far. We critically survey the existing literature and report experiments on eight languages, comparing systems spanning all categories of proposed normalization techniques, analysing the effect of training data quantity, and using different evaluation methods. The datasets and scripts are made publicly available.
%R 10.18653/v1/N19-1389
%U https://aclanthology.org/N19-1389
%U https://doi.org/10.18653/v1/N19-1389
%P 3885-3898
Markdown (Informal)
[A Large-Scale Comparison of Historical Text Normalization Systems](https://aclanthology.org/N19-1389) (Bollmann, NAACL 2019)
ACL
- Marcel Bollmann. 2019. A Large-Scale Comparison of Historical Text Normalization Systems. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3885–3898, Minneapolis, Minnesota. Association for Computational Linguistics.