@inproceedings{ma-etal-2019-results,
title = "Results of the {WMT}19 Metrics Shared Task: Segment-Level and Strong {MT} Systems Pose Big Challenges",
author = "Ma, Qingsong and
Wei, Johnny and
Bojar, Ond{\v{r}}ej and
Graham, Yvette",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5302",
doi = "10.18653/v1/W19-5302",
pages = "62--90",
abstract = "This paper presents the results of the WMT19 Metrics Shared Task. Participants were asked to score the outputs of the translations systems competing in the WMT19 News Translation Task with automatic metrics. 13 research groups submitted 24 metrics, 10 of which are reference-less {``}metrics{''} and constitute submissions to the joint task with WMT19 Quality Estimation Task, {``}QE as a Metric{''}. In addition, we computed 11 baseline metrics, with 8 commonly applied baselines (BLEU, SentBLEU, NIST, WER, PER, TER, CDER, and chrF) and 3 reimplementations (chrF+, sacreBLEU-BLEU, and sacreBLEU-chrF). Metrics were evaluated on the system level, how well a given metric correlates with the WMT19 official manual ranking, and segment level, how well the metric correlates with human judgements of segment quality. This year, we use direct assessment (DA) as our only form of manual evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2019-results">
<titleInfo>
<title>Results of the WMT19 Metrics Shared Task: Segment-Level and Strong MT Systems Pose Big Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qingsong</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johnny</namePart>
<namePart type="family">Wei</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>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the results of the WMT19 Metrics Shared Task. Participants were asked to score the outputs of the translations systems competing in the WMT19 News Translation Task with automatic metrics. 13 research groups submitted 24 metrics, 10 of which are reference-less “metrics” and constitute submissions to the joint task with WMT19 Quality Estimation Task, “QE as a Metric”. In addition, we computed 11 baseline metrics, with 8 commonly applied baselines (BLEU, SentBLEU, NIST, WER, PER, TER, CDER, and chrF) and 3 reimplementations (chrF+, sacreBLEU-BLEU, and sacreBLEU-chrF). Metrics were evaluated on the system level, how well a given metric correlates with the WMT19 official manual ranking, and segment level, how well the metric correlates with human judgements of segment quality. This year, we use direct assessment (DA) as our only form of manual evaluation.</abstract>
<identifier type="citekey">ma-etal-2019-results</identifier>
<identifier type="doi">10.18653/v1/W19-5302</identifier>
<location>
<url>https://aclanthology.org/W19-5302</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>62</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Results of the WMT19 Metrics Shared Task: Segment-Level and Strong MT Systems Pose Big Challenges
%A Ma, Qingsong
%A Wei, Johnny
%A Bojar, Ondřej
%A Graham, Yvette
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F ma-etal-2019-results
%X This paper presents the results of the WMT19 Metrics Shared Task. Participants were asked to score the outputs of the translations systems competing in the WMT19 News Translation Task with automatic metrics. 13 research groups submitted 24 metrics, 10 of which are reference-less “metrics” and constitute submissions to the joint task with WMT19 Quality Estimation Task, “QE as a Metric”. In addition, we computed 11 baseline metrics, with 8 commonly applied baselines (BLEU, SentBLEU, NIST, WER, PER, TER, CDER, and chrF) and 3 reimplementations (chrF+, sacreBLEU-BLEU, and sacreBLEU-chrF). Metrics were evaluated on the system level, how well a given metric correlates with the WMT19 official manual ranking, and segment level, how well the metric correlates with human judgements of segment quality. This year, we use direct assessment (DA) as our only form of manual evaluation.
%R 10.18653/v1/W19-5302
%U https://aclanthology.org/W19-5302
%U https://doi.org/10.18653/v1/W19-5302
%P 62-90
Markdown (Informal)
[Results of the WMT19 Metrics Shared Task: Segment-Level and Strong MT Systems Pose Big Challenges](https://aclanthology.org/W19-5302) (Ma et al., WMT 2019)
ACL