@inproceedings{popovic-2019-evaluating,
title = "Evaluating Conjunction Disambiguation on {E}nglish-to-{G}erman and {F}rench-to-{G}erman {WMT} 2019 Translation Hypotheses",
author = "Popovi{\'c}, Maja",
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/W19-5353",
doi = "10.18653/v1/W19-5353",
pages = "464--469",
abstract = "We present a test set for evaluating an MT system{'}s capability to translate ambiguous conjunctions depending on the sentence structure. We concentrate on the English conjunction {``}but{''} and its French equivalent {``}mais{''} which can be translated into two different German conjunctions. We evaluate all English-to-German and French-to-German submissions to the WMT 2019 shared translation task. The evaluation is done mainly automatically, with additional fast manual inspection of unclear cases. All systems almost perfectly recognise the target conjunction {``}aber{''}, whereas accuracies for the other target conjunction {``}sondern{''} range from 78{\%} to 97{\%}, and the errors are mostly caused by replacing it with the alternative conjunction {``}aber{''}. The best performing system for both language pairs is a multilingual Transformer {``}TartuNLP{''} system trained on all WMT 2019 language pairs which use the Latin script, indicating that the multilingual approach is beneficial for conjunction disambiguation. As for other system features, such as using synthetic back-translated data, context-aware, hybrid, etc., no particular (dis)advantages can be observed. Qualitative manual inspection of translation hypotheses shown that highly ranked systems generally produce translations with high adequacy and fluency, meaning that these systems are not only capable of capturing the right conjunction whereas the rest of the translation hypothesis is poor. On the other hand, the low ranked systems generally exhibit lower fluency and poor adequacy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popovic-2019-evaluating">
<titleInfo>
<title>Evaluating Conjunction Disambiguation on English-to-German and French-to-German WMT 2019 Translation Hypotheses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</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>We present a test set for evaluating an MT system’s capability to translate ambiguous conjunctions depending on the sentence structure. We concentrate on the English conjunction “but” and its French equivalent “mais” which can be translated into two different German conjunctions. We evaluate all English-to-German and French-to-German submissions to the WMT 2019 shared translation task. The evaluation is done mainly automatically, with additional fast manual inspection of unclear cases. All systems almost perfectly recognise the target conjunction “aber”, whereas accuracies for the other target conjunction “sondern” range from 78% to 97%, and the errors are mostly caused by replacing it with the alternative conjunction “aber”. The best performing system for both language pairs is a multilingual Transformer “TartuNLP” system trained on all WMT 2019 language pairs which use the Latin script, indicating that the multilingual approach is beneficial for conjunction disambiguation. As for other system features, such as using synthetic back-translated data, context-aware, hybrid, etc., no particular (dis)advantages can be observed. Qualitative manual inspection of translation hypotheses shown that highly ranked systems generally produce translations with high adequacy and fluency, meaning that these systems are not only capable of capturing the right conjunction whereas the rest of the translation hypothesis is poor. On the other hand, the low ranked systems generally exhibit lower fluency and poor adequacy.</abstract>
<identifier type="citekey">popovic-2019-evaluating</identifier>
<identifier type="doi">10.18653/v1/W19-5353</identifier>
<location>
<url>https://aclanthology.org/W19-5353</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>464</start>
<end>469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Conjunction Disambiguation on English-to-German and French-to-German WMT 2019 Translation Hypotheses
%A Popović, Maja
%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 popovic-2019-evaluating
%X We present a test set for evaluating an MT system’s capability to translate ambiguous conjunctions depending on the sentence structure. We concentrate on the English conjunction “but” and its French equivalent “mais” which can be translated into two different German conjunctions. We evaluate all English-to-German and French-to-German submissions to the WMT 2019 shared translation task. The evaluation is done mainly automatically, with additional fast manual inspection of unclear cases. All systems almost perfectly recognise the target conjunction “aber”, whereas accuracies for the other target conjunction “sondern” range from 78% to 97%, and the errors are mostly caused by replacing it with the alternative conjunction “aber”. The best performing system for both language pairs is a multilingual Transformer “TartuNLP” system trained on all WMT 2019 language pairs which use the Latin script, indicating that the multilingual approach is beneficial for conjunction disambiguation. As for other system features, such as using synthetic back-translated data, context-aware, hybrid, etc., no particular (dis)advantages can be observed. Qualitative manual inspection of translation hypotheses shown that highly ranked systems generally produce translations with high adequacy and fluency, meaning that these systems are not only capable of capturing the right conjunction whereas the rest of the translation hypothesis is poor. On the other hand, the low ranked systems generally exhibit lower fluency and poor adequacy.
%R 10.18653/v1/W19-5353
%U https://aclanthology.org/W19-5353
%U https://doi.org/10.18653/v1/W19-5353
%P 464-469
Markdown (Informal)
[Evaluating Conjunction Disambiguation on English-to-German and French-to-German WMT 2019 Translation Hypotheses](https://aclanthology.org/W19-5353) (Popović, WMT 2019)
ACL