@inproceedings{kreutzer-etal-2020-correct,
title = "Correct Me If You Can: Learning from Error Corrections and Markings",
author = "Kreutzer, Julia and
Berger, Nathaniel and
Riezler, Stefan",
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.15",
pages = "135--144",
abstract = "Sequence-to-sequence learning involves a trade-off between signal strength and annotation cost of training data. For example, machine translation data range from costly expert-generated translations that enable supervised learning, to weak quality-judgment feedback that facilitate reinforcement learning. We present the first user study on annotation cost and machine learnability for the less popular annotation mode of error markings. We show that error markings for translations of TED talks from English to German allow precise credit assignment while requiring significantly less human effort than correcting/post-editing, and that error-marked data can be used successfully to fine-tune neural machine translation models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kreutzer-etal-2020-correct">
<titleInfo>
<title>Correct Me If You Can: Learning from Error Corrections and Markings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Kreutzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Berger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Riezler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Lisboa, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sequence-to-sequence learning involves a trade-off between signal strength and annotation cost of training data. For example, machine translation data range from costly expert-generated translations that enable supervised learning, to weak quality-judgment feedback that facilitate reinforcement learning. We present the first user study on annotation cost and machine learnability for the less popular annotation mode of error markings. We show that error markings for translations of TED talks from English to German allow precise credit assignment while requiring significantly less human effort than correcting/post-editing, and that error-marked data can be used successfully to fine-tune neural machine translation models.</abstract>
<identifier type="citekey">kreutzer-etal-2020-correct</identifier>
<location>
<url>https://aclanthology.org/2020.eamt-1.15</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>135</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Correct Me If You Can: Learning from Error Corrections and Markings
%A Kreutzer, Julia
%A Berger, Nathaniel
%A Riezler, Stefan
%S Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
%D 2020
%8 nov
%I European Association for Machine Translation
%C Lisboa, Portugal
%F kreutzer-etal-2020-correct
%X Sequence-to-sequence learning involves a trade-off between signal strength and annotation cost of training data. For example, machine translation data range from costly expert-generated translations that enable supervised learning, to weak quality-judgment feedback that facilitate reinforcement learning. We present the first user study on annotation cost and machine learnability for the less popular annotation mode of error markings. We show that error markings for translations of TED talks from English to German allow precise credit assignment while requiring significantly less human effort than correcting/post-editing, and that error-marked data can be used successfully to fine-tune neural machine translation models.
%U https://aclanthology.org/2020.eamt-1.15
%P 135-144
Markdown (Informal)
[Correct Me If You Can: Learning from Error Corrections and Markings](https://aclanthology.org/2020.eamt-1.15) (Kreutzer et al., EAMT 2020)
ACL