@inproceedings{sudoh-etal-2021-translation,
title = "Is This Translation Error Critical?: Classification-Based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors",
author = "Sudoh, Katsuhito and
Takahashi, Kosuke and
Nakamura, Satoshi",
editor = "Belz, Anya and
Agarwal, Shubham and
Graham, Yvette and
Reiter, Ehud and
Shimorina, Anastasia",
booktitle = "Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.humeval-1.5",
pages = "46--55",
abstract = "This paper discusses a classification-based approach to machine translation evaluation, as opposed to a common regression-based approach in the WMT Metrics task. Recent machine translation usually works well but sometimes makes critical errors due to just a few wrong word choices. Our classification-based approach focuses on such errors using several error type labels, for practical machine translation evaluation in an age of neural machine translation. We made additional annotations on the WMT 2015-2017 Metrics datasets with fluency and adequacy labels to distinguish different types of translation errors from syntactic and semantic viewpoints. We present our human evaluation criteria for the corpus development and automatic evaluation experiments using the corpus. The human evaluation corpus will be publicly available upon publication.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sudoh-etal-2021-translation">
<titleInfo>
<title>Is This Translation Error Critical?: Classification-Based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses a classification-based approach to machine translation evaluation, as opposed to a common regression-based approach in the WMT Metrics task. Recent machine translation usually works well but sometimes makes critical errors due to just a few wrong word choices. Our classification-based approach focuses on such errors using several error type labels, for practical machine translation evaluation in an age of neural machine translation. We made additional annotations on the WMT 2015-2017 Metrics datasets with fluency and adequacy labels to distinguish different types of translation errors from syntactic and semantic viewpoints. We present our human evaluation criteria for the corpus development and automatic evaluation experiments using the corpus. The human evaluation corpus will be publicly available upon publication.</abstract>
<identifier type="citekey">sudoh-etal-2021-translation</identifier>
<location>
<url>https://aclanthology.org/2021.humeval-1.5</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>46</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is This Translation Error Critical?: Classification-Based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors
%A Sudoh, Katsuhito
%A Takahashi, Kosuke
%A Nakamura, Satoshi
%Y Belz, Anya
%Y Agarwal, Shubham
%Y Graham, Yvette
%Y Reiter, Ehud
%Y Shimorina, Anastasia
%S Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F sudoh-etal-2021-translation
%X This paper discusses a classification-based approach to machine translation evaluation, as opposed to a common regression-based approach in the WMT Metrics task. Recent machine translation usually works well but sometimes makes critical errors due to just a few wrong word choices. Our classification-based approach focuses on such errors using several error type labels, for practical machine translation evaluation in an age of neural machine translation. We made additional annotations on the WMT 2015-2017 Metrics datasets with fluency and adequacy labels to distinguish different types of translation errors from syntactic and semantic viewpoints. We present our human evaluation criteria for the corpus development and automatic evaluation experiments using the corpus. The human evaluation corpus will be publicly available upon publication.
%U https://aclanthology.org/2021.humeval-1.5
%P 46-55
Markdown (Informal)
[Is This Translation Error Critical?: Classification-Based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors](https://aclanthology.org/2021.humeval-1.5) (Sudoh et al., HumEval 2021)
ACL