@inproceedings{snover-etal-2006-study,
title = "A Study of Translation Edit Rate with Targeted Human Annotation",
author = "Snover, Matthew and
Dorr, Bonnie and
Schwartz, Rich and
Micciulla, Linnea and
Makhoul, John",
booktitle = "Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = aug # " 8-12",
year = "2006",
address = "Cambridge, Massachusetts, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2006.amta-papers.25",
pages = "223--231",
abstract = "We examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments. Translation Edit Rate (TER) measures the amount of editing that a human would have to perform to change a system output so it exactly matches a reference translation. We show that the single-reference variant of TER correlates as well with human judgments of MT quality as the four-reference variant of BLEU. We also define a human-targeted TER (or HTER) and show that it yields higher correlations with human judgments than BLEU{---}even when BLEU is given human-targeted references. Our results indicate that HTER correlates with human judgments better than HMETEOR and that the four-reference variants of TER and HTER correlate with human judgments as well as{---}or better than{---}a second human judgment does.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="snover-etal-2006-study">
<titleInfo>
<title>A Study of Translation Edit Rate with Targeted Human Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Snover</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Dorr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rich</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linnea</namePart>
<namePart type="family">Micciulla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Makhoul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-aug" 8-12"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Cambridge, Massachusetts, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments. Translation Edit Rate (TER) measures the amount of editing that a human would have to perform to change a system output so it exactly matches a reference translation. We show that the single-reference variant of TER correlates as well with human judgments of MT quality as the four-reference variant of BLEU. We also define a human-targeted TER (or HTER) and show that it yields higher correlations with human judgments than BLEU—even when BLEU is given human-targeted references. Our results indicate that HTER correlates with human judgments better than HMETEOR and that the four-reference variants of TER and HTER correlate with human judgments as well as—or better than—a second human judgment does.</abstract>
<identifier type="citekey">snover-etal-2006-study</identifier>
<location>
<url>https://aclanthology.org/2006.amta-papers.25</url>
</location>
<part>
<date>2006-aug" 8-12"</date>
<extent unit="page">
<start>223</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Study of Translation Edit Rate with Targeted Human Annotation
%A Snover, Matthew
%A Dorr, Bonnie
%A Schwartz, Rich
%A Micciulla, Linnea
%A Makhoul, John
%S Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 2006
%8 aug" 8 12"
%I Association for Machine Translation in the Americas
%C Cambridge, Massachusetts, USA
%F snover-etal-2006-study
%X We examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments. Translation Edit Rate (TER) measures the amount of editing that a human would have to perform to change a system output so it exactly matches a reference translation. We show that the single-reference variant of TER correlates as well with human judgments of MT quality as the four-reference variant of BLEU. We also define a human-targeted TER (or HTER) and show that it yields higher correlations with human judgments than BLEU—even when BLEU is given human-targeted references. Our results indicate that HTER correlates with human judgments better than HMETEOR and that the four-reference variants of TER and HTER correlate with human judgments as well as—or better than—a second human judgment does.
%U https://aclanthology.org/2006.amta-papers.25
%P 223-231
Markdown (Informal)
[A Study of Translation Edit Rate with Targeted Human Annotation](https://aclanthology.org/2006.amta-papers.25) (Snover et al., AMTA 2006)
ACL
- Matthew Snover, Bonnie Dorr, Rich Schwartz, Linnea Micciulla, and John Makhoul. 2006. A Study of Translation Edit Rate with Targeted Human Annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 223–231, Cambridge, Massachusetts, USA. Association for Machine Translation in the Americas.