@inproceedings{yankovskaya-etal-2019-quality,
title = "Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings",
author = {Yankovskaya, Elizaveta and
T{\"a}ttar, Andre and
Fishel, Mark},
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5410",
doi = "10.18653/v1/W19-5410",
pages = "101--105",
abstract = "We propose the use of pre-trained embeddings as features of a regression model for sentence-level quality estimation of machine translation. In our work we combine freely available BERT and LASER multilingual embeddings to train a neural-based regression model. In the second proposed method we use as an input features not only pre-trained embeddings, but also log probability of any machine translation (MT) system. Both methods are applied to several language pairs and are evaluated both as a classical quality estimation system (predicting the HTER score) as well as an MT metric (predicting human judgements of translation quality).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yankovskaya-etal-2019-quality">
<titleInfo>
<title>Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizaveta</namePart>
<namePart type="family">Yankovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Tättar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose the use of pre-trained embeddings as features of a regression model for sentence-level quality estimation of machine translation. In our work we combine freely available BERT and LASER multilingual embeddings to train a neural-based regression model. In the second proposed method we use as an input features not only pre-trained embeddings, but also log probability of any machine translation (MT) system. Both methods are applied to several language pairs and are evaluated both as a classical quality estimation system (predicting the HTER score) as well as an MT metric (predicting human judgements of translation quality).</abstract>
<identifier type="citekey">yankovskaya-etal-2019-quality</identifier>
<identifier type="doi">10.18653/v1/W19-5410</identifier>
<location>
<url>https://aclanthology.org/W19-5410</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>101</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings
%A Yankovskaya, Elizaveta
%A Tättar, Andre
%A Fishel, Mark
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F yankovskaya-etal-2019-quality
%X We propose the use of pre-trained embeddings as features of a regression model for sentence-level quality estimation of machine translation. In our work we combine freely available BERT and LASER multilingual embeddings to train a neural-based regression model. In the second proposed method we use as an input features not only pre-trained embeddings, but also log probability of any machine translation (MT) system. Both methods are applied to several language pairs and are evaluated both as a classical quality estimation system (predicting the HTER score) as well as an MT metric (predicting human judgements of translation quality).
%R 10.18653/v1/W19-5410
%U https://aclanthology.org/W19-5410
%U https://doi.org/10.18653/v1/W19-5410
%P 101-105
Markdown (Informal)
[Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings](https://aclanthology.org/W19-5410) (Yankovskaya et al., 2019)
ACL