@inproceedings{guillou-etal-2018-pronoun,
title = "A Pronoun Test Suite Evaluation of the {E}nglish{--}{G}erman {MT} Systems at {WMT} 2018",
author = "Guillou, Liane and
Hardmeier, Christian and
Lapshinova-Koltunski, Ekaterina and
Lo{\'a}iciga, Sharid",
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
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Specia, Lucia and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6435",
doi = "10.18653/v1/W18-6435",
pages = "570--577",
abstract = "We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition. We work with a test suite specifically designed to assess system quality in various fine-grained categories known to be problematic. The main evaluation scores come from a semi-automatic process, combining automatic reference matching with extensive manual annotation of uncertain cases. We find that current NMT systems are good at translating pronouns with intra-sentential reference, but the inter-sentential cases remain difficult. NMT systems are also good at the translation of event pronouns, unlike systems from the phrase-based SMT paradigm. No single system performs best at translating all types of anaphoric pronouns, suggesting unexplained random effects influencing the translation of pronouns with NMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guillou-etal-2018-pronoun">
<titleInfo>
<title>A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liane</namePart>
<namePart type="family">Guillou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loáiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</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">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">Lucia</namePart>
<namePart type="family">Specia</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">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition. We work with a test suite specifically designed to assess system quality in various fine-grained categories known to be problematic. The main evaluation scores come from a semi-automatic process, combining automatic reference matching with extensive manual annotation of uncertain cases. We find that current NMT systems are good at translating pronouns with intra-sentential reference, but the inter-sentential cases remain difficult. NMT systems are also good at the translation of event pronouns, unlike systems from the phrase-based SMT paradigm. No single system performs best at translating all types of anaphoric pronouns, suggesting unexplained random effects influencing the translation of pronouns with NMT.</abstract>
<identifier type="citekey">guillou-etal-2018-pronoun</identifier>
<identifier type="doi">10.18653/v1/W18-6435</identifier>
<location>
<url>https://aclanthology.org/W18-6435</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>570</start>
<end>577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018
%A Guillou, Liane
%A Hardmeier, Christian
%A Lapshinova-Koltunski, Ekaterina
%A Loáiciga, Sharid
%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 Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Specia, Lucia
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Belgium, Brussels
%F guillou-etal-2018-pronoun
%X We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition. We work with a test suite specifically designed to assess system quality in various fine-grained categories known to be problematic. The main evaluation scores come from a semi-automatic process, combining automatic reference matching with extensive manual annotation of uncertain cases. We find that current NMT systems are good at translating pronouns with intra-sentential reference, but the inter-sentential cases remain difficult. NMT systems are also good at the translation of event pronouns, unlike systems from the phrase-based SMT paradigm. No single system performs best at translating all types of anaphoric pronouns, suggesting unexplained random effects influencing the translation of pronouns with NMT.
%R 10.18653/v1/W18-6435
%U https://aclanthology.org/W18-6435
%U https://doi.org/10.18653/v1/W18-6435
%P 570-577
Markdown (Informal)
[A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018](https://aclanthology.org/W18-6435) (Guillou et al., WMT 2018)
ACL