@inproceedings{cambra-nunziatini-2022-need,
title = "All You Need is Source! A Study on Source-based Quality Estimation for Neural Machine Translation",
author = "Cambra, Jon and
Nunziatini, Mara",
editor = "Campbell, Janice and
Larocca, Stephen and
Marciano, Jay and
Savenkov, Konstantin and
Yanishevsky, Alex",
booktitle = "Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)",
month = sep,
year = "2022",
address = "Orlando, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2022.amta-upg.15",
pages = "210--220",
abstract = "Segment-level Quality Estimation (QE) is an increasingly sought-after task in the Machine Translation (MT) industry. In recent years, it has experienced an impressive evolution not only thanks to the implementation of supervised models using source and hypothesis information, but also through the usage of MT probabilities. This work presents a different approach to QE where only the source segment and the Neural MT (NMT) training data are needed, making possible an approximation to translation quality before inference. Our work is based on the idea that NMT quality at a segment level depends on the similarity degree between the source segment to be translated and the engine{'}s training data. The features proposed measuring this aspect of data achieve competitive correlations with MT metrics and human judgment and prove to be advantageous for post-editing (PE) prioritization task with domain adapted engines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cambra-nunziatini-2022-need">
<titleInfo>
<title>All You Need is Source! A Study on Source-based Quality Estimation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Cambra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janice</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Larocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Marciano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Savenkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Yanishevsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Orlando, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Segment-level Quality Estimation (QE) is an increasingly sought-after task in the Machine Translation (MT) industry. In recent years, it has experienced an impressive evolution not only thanks to the implementation of supervised models using source and hypothesis information, but also through the usage of MT probabilities. This work presents a different approach to QE where only the source segment and the Neural MT (NMT) training data are needed, making possible an approximation to translation quality before inference. Our work is based on the idea that NMT quality at a segment level depends on the similarity degree between the source segment to be translated and the engine’s training data. The features proposed measuring this aspect of data achieve competitive correlations with MT metrics and human judgment and prove to be advantageous for post-editing (PE) prioritization task with domain adapted engines.</abstract>
<identifier type="citekey">cambra-nunziatini-2022-need</identifier>
<location>
<url>https://aclanthology.org/2022.amta-upg.15</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>210</start>
<end>220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T All You Need is Source! A Study on Source-based Quality Estimation for Neural Machine Translation
%A Cambra, Jon
%A Nunziatini, Mara
%Y Campbell, Janice
%Y Larocca, Stephen
%Y Marciano, Jay
%Y Savenkov, Konstantin
%Y Yanishevsky, Alex
%S Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F cambra-nunziatini-2022-need
%X Segment-level Quality Estimation (QE) is an increasingly sought-after task in the Machine Translation (MT) industry. In recent years, it has experienced an impressive evolution not only thanks to the implementation of supervised models using source and hypothesis information, but also through the usage of MT probabilities. This work presents a different approach to QE where only the source segment and the Neural MT (NMT) training data are needed, making possible an approximation to translation quality before inference. Our work is based on the idea that NMT quality at a segment level depends on the similarity degree between the source segment to be translated and the engine’s training data. The features proposed measuring this aspect of data achieve competitive correlations with MT metrics and human judgment and prove to be advantageous for post-editing (PE) prioritization task with domain adapted engines.
%U https://aclanthology.org/2022.amta-upg.15
%P 210-220
Markdown (Informal)
[All You Need is Source! A Study on Source-based Quality Estimation for Neural Machine Translation](https://aclanthology.org/2022.amta-upg.15) (Cambra & Nunziatini, AMTA 2022)
ACL