@inproceedings{wang-merlo-2016-modifications,
title = "Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings",
author = "Wang, Haozhou and
Merlo, Paola",
editor = "Lambert, Patrik and
Babych, Bogdan and
Eberle, Kurt and
Banchs, Rafael E. and
Rapp, Reinhard and
Costa-juss{\`a}, Marta R.",
booktitle = "Proceedings of the Sixth Workshop on Hybrid Approaches to Translation ({H}y{T}ra6)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4505",
pages = "33--41",
abstract = "Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching. In this paper, we propose some modifications to the traditional measures based on word embeddings for these two metrics. The evaluation results show that our modifications significantly improve their correlation with human judgements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-merlo-2016-modifications">
<titleInfo>
<title>Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haozhou</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrik</namePart>
<namePart type="family">Lambert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurt</namePart>
<namePart type="family">Eberle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Banchs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching. In this paper, we propose some modifications to the traditional measures based on word embeddings for these two metrics. The evaluation results show that our modifications significantly improve their correlation with human judgements.</abstract>
<identifier type="citekey">wang-merlo-2016-modifications</identifier>
<location>
<url>https://aclanthology.org/W16-4505</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>33</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings
%A Wang, Haozhou
%A Merlo, Paola
%Y Lambert, Patrik
%Y Babych, Bogdan
%Y Eberle, Kurt
%Y Banchs, Rafael E.
%Y Rapp, Reinhard
%Y Costa-jussà, Marta R.
%S Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F wang-merlo-2016-modifications
%X Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching. In this paper, we propose some modifications to the traditional measures based on word embeddings for these two metrics. The evaluation results show that our modifications significantly improve their correlation with human judgements.
%U https://aclanthology.org/W16-4505
%P 33-41
Markdown (Informal)
[Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings](https://aclanthology.org/W16-4505) (Wang & Merlo, HyTra 2016)
ACL