@inproceedings{yankovskaya-fishel-2021-direct,
title = "Direct Exploitation of Attention Weights for Translation Quality Estimation",
author = "Yankovskaya, Lisa and
Fishel, Mark",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.101",
pages = "955--960",
abstract = "The paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach based on attention weights extracted from machine translation systems. In contrast to the previous works, we directly explore attention weight matrices without replacing them with general metrics (like entropy). We show that some of our models can be trained with a small amount of a high-cost labelled data. In the absence of training data our approach still demonstrates a moderate linear correlation, when trained with synthetic data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yankovskaya-fishel-2021-direct">
<titleInfo>
<title>Direct Exploitation of Attention Weights for Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Yankovskaya</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>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach based on attention weights extracted from machine translation systems. In contrast to the previous works, we directly explore attention weight matrices without replacing them with general metrics (like entropy). We show that some of our models can be trained with a small amount of a high-cost labelled data. In the absence of training data our approach still demonstrates a moderate linear correlation, when trained with synthetic data.</abstract>
<identifier type="citekey">yankovskaya-fishel-2021-direct</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.101</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>955</start>
<end>960</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Direct Exploitation of Attention Weights for Translation Quality Estimation
%A Yankovskaya, Lisa
%A Fishel, Mark
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F yankovskaya-fishel-2021-direct
%X The paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach based on attention weights extracted from machine translation systems. In contrast to the previous works, we directly explore attention weight matrices without replacing them with general metrics (like entropy). We show that some of our models can be trained with a small amount of a high-cost labelled data. In the absence of training data our approach still demonstrates a moderate linear correlation, when trained with synthetic data.
%U https://aclanthology.org/2021.wmt-1.101
%P 955-960
Markdown (Informal)
[Direct Exploitation of Attention Weights for Translation Quality Estimation](https://aclanthology.org/2021.wmt-1.101) (Yankovskaya & Fishel, WMT 2021)
ACL