@inproceedings{behnke-etal-2022-bias,
title = "Bias Mitigation in Machine Translation Quality Estimation",
author = "Behnke, Hanna and
Fomicheva, Marina and
Specia, Lucia",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.104",
doi = "10.18653/v1/2022.acl-long.104",
pages = "1475--1487",
abstract = "Machine Translation Quality Estimation (QE) aims to build predictive models to assess the quality of machine-generated translations in the absence of reference translations. While state-of-the-art QE models have been shown to achieve good results, they over-rely on features that do not have a causal impact on the quality of a translation. In particular, there appears to be a partial input bias, i.e., a tendency to assign high-quality scores to translations that are fluent and grammatically correct, even though they do not preserve the meaning of the source. We analyse the partial input bias in further detail and evaluate four approaches to use auxiliary tasks for bias mitigation. Two approaches use additional data to inform and support the main task, while the other two are adversarial, actively discouraging the model from learning the bias. We compare the methods with respect to their ability to reduce the partial input bias while maintaining the overall performance. We find that training a multitask architecture with an auxiliary binary classification task that utilises additional augmented data best achieves the desired effects and generalises well to different languages and quality metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="behnke-etal-2022-bias">
<titleInfo>
<title>Bias Mitigation in Machine Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Behnke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine Translation Quality Estimation (QE) aims to build predictive models to assess the quality of machine-generated translations in the absence of reference translations. While state-of-the-art QE models have been shown to achieve good results, they over-rely on features that do not have a causal impact on the quality of a translation. In particular, there appears to be a partial input bias, i.e., a tendency to assign high-quality scores to translations that are fluent and grammatically correct, even though they do not preserve the meaning of the source. We analyse the partial input bias in further detail and evaluate four approaches to use auxiliary tasks for bias mitigation. Two approaches use additional data to inform and support the main task, while the other two are adversarial, actively discouraging the model from learning the bias. We compare the methods with respect to their ability to reduce the partial input bias while maintaining the overall performance. We find that training a multitask architecture with an auxiliary binary classification task that utilises additional augmented data best achieves the desired effects and generalises well to different languages and quality metrics.</abstract>
<identifier type="citekey">behnke-etal-2022-bias</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.104</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.104</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1475</start>
<end>1487</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bias Mitigation in Machine Translation Quality Estimation
%A Behnke, Hanna
%A Fomicheva, Marina
%A Specia, Lucia
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F behnke-etal-2022-bias
%X Machine Translation Quality Estimation (QE) aims to build predictive models to assess the quality of machine-generated translations in the absence of reference translations. While state-of-the-art QE models have been shown to achieve good results, they over-rely on features that do not have a causal impact on the quality of a translation. In particular, there appears to be a partial input bias, i.e., a tendency to assign high-quality scores to translations that are fluent and grammatically correct, even though they do not preserve the meaning of the source. We analyse the partial input bias in further detail and evaluate four approaches to use auxiliary tasks for bias mitigation. Two approaches use additional data to inform and support the main task, while the other two are adversarial, actively discouraging the model from learning the bias. We compare the methods with respect to their ability to reduce the partial input bias while maintaining the overall performance. We find that training a multitask architecture with an auxiliary binary classification task that utilises additional augmented data best achieves the desired effects and generalises well to different languages and quality metrics.
%R 10.18653/v1/2022.acl-long.104
%U https://aclanthology.org/2022.acl-long.104
%U https://doi.org/10.18653/v1/2022.acl-long.104
%P 1475-1487
Markdown (Informal)
[Bias Mitigation in Machine Translation Quality Estimation](https://aclanthology.org/2022.acl-long.104) (Behnke et al., ACL 2022)
ACL
- Hanna Behnke, Marina Fomicheva, and Lucia Specia. 2022. Bias Mitigation in Machine Translation Quality Estimation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1475–1487, Dublin, Ireland. Association for Computational Linguistics.