@inproceedings{perrella-etal-2022-matese,
title = "{M}a{TES}e: Machine Translation Evaluation as a Sequence Tagging Problem",
author = "Perrella, Stefano and
Proietti, Lorenzo and
Scir{\`e}, Alessandro and
Campolungo, Niccol{\`o} and
Navigli, Roberto",
booktitle = "Proceedings of the Seventh Conference on Machine Translation (WMT)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wmt-1.51",
pages = "569--577",
abstract = "Starting from last year, WMT human evaluation has been performed within the Multidimensional Quality Metrics (MQM) framework, where human annotators are asked to identify error spans in translations, alongside an error category and a severity. In this paper, we describe our submission to the WMT 2022 Metrics Shared Task, where we propose using the same paradigm for automatic evaluation: we present the MaTESe metrics, which reframe machine translation evaluation as a sequence tagging problem. Our submission also includes a reference-free metric, denominated MaTESe-QE. Despite the paucity of the openly available MQM data, our metrics obtain promising results, showing high levels of correlation with human judgements, while also enabling an evaluation that is interpretable. Moreover, MaTESe-QE can also be employed in settings where it is infeasible to curate reference translations manually.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="perrella-etal-2022-matese">
<titleInfo>
<title>MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Perrella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Proietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Scirè</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niccolò</namePart>
<namePart type="family">Campolungo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Conference on Machine Translation (WMT)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Starting from last year, WMT human evaluation has been performed within the Multidimensional Quality Metrics (MQM) framework, where human annotators are asked to identify error spans in translations, alongside an error category and a severity. In this paper, we describe our submission to the WMT 2022 Metrics Shared Task, where we propose using the same paradigm for automatic evaluation: we present the MaTESe metrics, which reframe machine translation evaluation as a sequence tagging problem. Our submission also includes a reference-free metric, denominated MaTESe-QE. Despite the paucity of the openly available MQM data, our metrics obtain promising results, showing high levels of correlation with human judgements, while also enabling an evaluation that is interpretable. Moreover, MaTESe-QE can also be employed in settings where it is infeasible to curate reference translations manually.</abstract>
<identifier type="citekey">perrella-etal-2022-matese</identifier>
<location>
<url>https://aclanthology.org/2022.wmt-1.51</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>569</start>
<end>577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem
%A Perrella, Stefano
%A Proietti, Lorenzo
%A Scirè, Alessandro
%A Campolungo, Niccolò
%A Navigli, Roberto
%S Proceedings of the Seventh Conference on Machine Translation (WMT)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F perrella-etal-2022-matese
%X Starting from last year, WMT human evaluation has been performed within the Multidimensional Quality Metrics (MQM) framework, where human annotators are asked to identify error spans in translations, alongside an error category and a severity. In this paper, we describe our submission to the WMT 2022 Metrics Shared Task, where we propose using the same paradigm for automatic evaluation: we present the MaTESe metrics, which reframe machine translation evaluation as a sequence tagging problem. Our submission also includes a reference-free metric, denominated MaTESe-QE. Despite the paucity of the openly available MQM data, our metrics obtain promising results, showing high levels of correlation with human judgements, while also enabling an evaluation that is interpretable. Moreover, MaTESe-QE can also be employed in settings where it is infeasible to curate reference translations manually.
%U https://aclanthology.org/2022.wmt-1.51
%P 569-577
Markdown (Informal)
[MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem](https://aclanthology.org/2022.wmt-1.51) (Perrella et al., WMT 2022)
ACL
- Stefano Perrella, Lorenzo Proietti, Alessandro Scirè, Niccolò Campolungo, and Roberto Navigli. 2022. MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 569–577, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.