@inproceedings{guo-etal-2018-meteor,
title = "{M}eteor++: Incorporating Copy Knowledge into Machine Translation Evaluation",
author = "Guo, Yinuo and
Ruan, Chong and
Hu, Junfeng",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6454",
doi = "10.18653/v1/W18-6454",
pages = "740--745",
abstract = "In machine translation evaluation, a good candidate translation can be regarded as a paraphrase of the reference. We notice that some words are always copied during paraphrasing, which we call \textbf{copy knowledge}. Considering the stability of such knowledge, a good candidate translation should contain all these words appeared in the reference sentence. Therefore, in this participation of the WMT{'}2018 metrics shared task we introduce a simple statistical method for copy knowledge extraction, and incorporate it into Meteor metric, resulting in a new machine translation metric \textbf{Meteor++}. Our experiments show that Meteor++ can nicely integrate copy knowledge and improve the performance significantly on WMT17 and WMT15 evaluation sets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2018-meteor">
<titleInfo>
<title>Meteor++: Incorporating Copy Knowledge into Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinuo</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In machine translation evaluation, a good candidate translation can be regarded as a paraphrase of the reference. We notice that some words are always copied during paraphrasing, which we call copy knowledge. Considering the stability of such knowledge, a good candidate translation should contain all these words appeared in the reference sentence. Therefore, in this participation of the WMT’2018 metrics shared task we introduce a simple statistical method for copy knowledge extraction, and incorporate it into Meteor metric, resulting in a new machine translation metric Meteor++. Our experiments show that Meteor++ can nicely integrate copy knowledge and improve the performance significantly on WMT17 and WMT15 evaluation sets.</abstract>
<identifier type="citekey">guo-etal-2018-meteor</identifier>
<identifier type="doi">10.18653/v1/W18-6454</identifier>
<location>
<url>https://aclanthology.org/W18-6454</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>740</start>
<end>745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meteor++: Incorporating Copy Knowledge into Machine Translation Evaluation
%A Guo, Yinuo
%A Ruan, Chong
%A Hu, Junfeng
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Belgium, Brussels
%F guo-etal-2018-meteor
%X In machine translation evaluation, a good candidate translation can be regarded as a paraphrase of the reference. We notice that some words are always copied during paraphrasing, which we call copy knowledge. Considering the stability of such knowledge, a good candidate translation should contain all these words appeared in the reference sentence. Therefore, in this participation of the WMT’2018 metrics shared task we introduce a simple statistical method for copy knowledge extraction, and incorporate it into Meteor metric, resulting in a new machine translation metric Meteor++. Our experiments show that Meteor++ can nicely integrate copy knowledge and improve the performance significantly on WMT17 and WMT15 evaluation sets.
%R 10.18653/v1/W18-6454
%U https://aclanthology.org/W18-6454
%U https://doi.org/10.18653/v1/W18-6454
%P 740-745
Markdown (Informal)
[Meteor++: Incorporating Copy Knowledge into Machine Translation Evaluation](https://aclanthology.org/W18-6454) (Guo et al., WMT 2018)
ACL