@inproceedings{makarov-clematide-2020-semi,
title = "Semi-supervised Contextual Historical Text Normalization",
author = "Makarov, Peter and
Clematide, Simon",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.650",
doi = "10.18653/v1/2020.acl-main.650",
pages = "7284--7295",
abstract = "Historical text normalization, the task of mapping historical word forms to their modern counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; Lusetti et al., 2018; Bollmann et al., 2018;Robertson and Goldwater, 2018; Bollmannet al., 2017; Korchagina, 2017). Yet, virtually all approaches suffer from the two limitations: 1) They consider a fully supervised setup, often with impractically large manually normalized datasets; 2) Normalization happens on words in isolation. By utilizing a simple generative normalization model and obtaining powerful contextualization from the target-side language model, we train accurate models with unlabeled historical data. In realistic training scenarios, our approach often leads to reduction in manually normalized data at the same accuracy levels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="makarov-clematide-2020-semi">
<titleInfo>
<title>Semi-supervised Contextual Historical Text Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Makarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Historical text normalization, the task of mapping historical word forms to their modern counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; Lusetti et al., 2018; Bollmann et al., 2018;Robertson and Goldwater, 2018; Bollmannet al., 2017; Korchagina, 2017). Yet, virtually all approaches suffer from the two limitations: 1) They consider a fully supervised setup, often with impractically large manually normalized datasets; 2) Normalization happens on words in isolation. By utilizing a simple generative normalization model and obtaining powerful contextualization from the target-side language model, we train accurate models with unlabeled historical data. In realistic training scenarios, our approach often leads to reduction in manually normalized data at the same accuracy levels.</abstract>
<identifier type="citekey">makarov-clematide-2020-semi</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.650</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.650</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>7284</start>
<end>7295</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-supervised Contextual Historical Text Normalization
%A Makarov, Peter
%A Clematide, Simon
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F makarov-clematide-2020-semi
%X Historical text normalization, the task of mapping historical word forms to their modern counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; Lusetti et al., 2018; Bollmann et al., 2018;Robertson and Goldwater, 2018; Bollmannet al., 2017; Korchagina, 2017). Yet, virtually all approaches suffer from the two limitations: 1) They consider a fully supervised setup, often with impractically large manually normalized datasets; 2) Normalization happens on words in isolation. By utilizing a simple generative normalization model and obtaining powerful contextualization from the target-side language model, we train accurate models with unlabeled historical data. In realistic training scenarios, our approach often leads to reduction in manually normalized data at the same accuracy levels.
%R 10.18653/v1/2020.acl-main.650
%U https://aclanthology.org/2020.acl-main.650
%U https://doi.org/10.18653/v1/2020.acl-main.650
%P 7284-7295
Markdown (Informal)
[Semi-supervised Contextual Historical Text Normalization](https://aclanthology.org/2020.acl-main.650) (Makarov & Clematide, ACL 2020)
ACL