@inproceedings{yankovskaya-etal-2018-quality,
title = "Quality Estimation with Force-Decoded Attention and Cross-lingual Embeddings",
author = {Yankovskaya, Elizaveta and
T{\"a}ttar, Andre and
Fishel, Mark},
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/W18-6466",
doi = "10.18653/v1/W18-6466",
pages = "816--821",
abstract = "This paper describes the submissions of the team from the University of Tartu for the sentence-level Quality Estimation shared task of WMT18. The proposed models use features based on attention weights of a neural machine translation system and cross-lingual phrase embeddings as input features of a regression model. Two of the proposed models require only a neural machine translation system with an attention mechanism with no additional resources. Results show that combining neural networks and baseline features leads to significant improvements over the baseline features alone.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yankovskaya-etal-2018-quality">
<titleInfo>
<title>Quality Estimation with Force-Decoded Attention and Cross-lingual 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>2018-oct</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>This paper describes the submissions of the team from the University of Tartu for the sentence-level Quality Estimation shared task of WMT18. The proposed models use features based on attention weights of a neural machine translation system and cross-lingual phrase embeddings as input features of a regression model. Two of the proposed models require only a neural machine translation system with an attention mechanism with no additional resources. Results show that combining neural networks and baseline features leads to significant improvements over the baseline features alone.</abstract>
<identifier type="citekey">yankovskaya-etal-2018-quality</identifier>
<identifier type="doi">10.18653/v1/W18-6466</identifier>
<location>
<url>https://aclanthology.org/W18-6466</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>816</start>
<end>821</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Estimation with Force-Decoded Attention and Cross-lingual Embeddings
%A Yankovskaya, Elizaveta
%A Tättar, Andre
%A Fishel, Mark
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F yankovskaya-etal-2018-quality
%X This paper describes the submissions of the team from the University of Tartu for the sentence-level Quality Estimation shared task of WMT18. The proposed models use features based on attention weights of a neural machine translation system and cross-lingual phrase embeddings as input features of a regression model. Two of the proposed models require only a neural machine translation system with an attention mechanism with no additional resources. Results show that combining neural networks and baseline features leads to significant improvements over the baseline features alone.
%R 10.18653/v1/W18-6466
%U https://aclanthology.org/W18-6466
%U https://doi.org/10.18653/v1/W18-6466
%P 816-821
Markdown (Informal)
[Quality Estimation with Force-Decoded Attention and Cross-lingual Embeddings](https://aclanthology.org/W18-6466) (Yankovskaya et al., 2018)
ACL