@inproceedings{tryhubyshyn-etal-2023-bad,
title = "Bad {MT} Systems are Good for Quality Estimation",
author = "Tryhubyshyn, Iryna and
Tamchyna, Ale{\v{s}} and
Bojar, Ond{\v{r}}ej",
editor = "Utiyama, Masao and
Wang, Rui",
booktitle = "Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track",
month = sep,
year = "2023",
address = "Macau SAR, China",
publisher = "Asia-Pacific Association for Machine Translation",
url = "https://aclanthology.org/2023.mtsummit-research.17",
pages = "200--208",
abstract = "Quality estimation (QE) is the task of predicting quality of outputs produced by machine translation (MT) systems. Currently, the highest-performing QE systems are supervised and require training on data with golden quality scores. In this paper, we investigate the impact of the quality of the underlying MT outputs on the performance of QE systems. We find that QE models trained on datasets with lower-quality translations often outperform those trained on higher-quality data. We also demonstrate that good performance can be achieved by using a mix of data from different MT systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tryhubyshyn-etal-2023-bad">
<titleInfo>
<title>Bad MT Systems are Good for Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Tryhubyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleš</namePart>
<namePart type="family">Tamchyna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asia-Pacific Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Macau SAR, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Quality estimation (QE) is the task of predicting quality of outputs produced by machine translation (MT) systems. Currently, the highest-performing QE systems are supervised and require training on data with golden quality scores. In this paper, we investigate the impact of the quality of the underlying MT outputs on the performance of QE systems. We find that QE models trained on datasets with lower-quality translations often outperform those trained on higher-quality data. We also demonstrate that good performance can be achieved by using a mix of data from different MT systems.</abstract>
<identifier type="citekey">tryhubyshyn-etal-2023-bad</identifier>
<location>
<url>https://aclanthology.org/2023.mtsummit-research.17</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>200</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bad MT Systems are Good for Quality Estimation
%A Tryhubyshyn, Iryna
%A Tamchyna, Aleš
%A Bojar, Ondřej
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F tryhubyshyn-etal-2023-bad
%X Quality estimation (QE) is the task of predicting quality of outputs produced by machine translation (MT) systems. Currently, the highest-performing QE systems are supervised and require training on data with golden quality scores. In this paper, we investigate the impact of the quality of the underlying MT outputs on the performance of QE systems. We find that QE models trained on datasets with lower-quality translations often outperform those trained on higher-quality data. We also demonstrate that good performance can be achieved by using a mix of data from different MT systems.
%U https://aclanthology.org/2023.mtsummit-research.17
%P 200-208
Markdown (Informal)
[Bad MT Systems are Good for Quality Estimation](https://aclanthology.org/2023.mtsummit-research.17) (Tryhubyshyn et al., MTSummit 2023)
ACL
- Iryna Tryhubyshyn, Aleš Tamchyna, and Ondřej Bojar. 2023. Bad MT Systems are Good for Quality Estimation. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 200–208, Macau SAR, China. Asia-Pacific Association for Machine Translation.