@inproceedings{sostaric-etal-2018-discourse,
title = "Discourse-Related Language Contrasts in {E}nglish-{C}roatian Human and Machine Translation",
author = "{\v{S}}o{\v{s}}tari{\'c}, Margita and
Hardmeier, Christian and
Stymne, Sara",
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: Research Papers",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6305",
doi = "10.18653/v1/W18-6305",
pages = "36--48",
abstract = "We present an analysis of a number of coreference phenomena in English-Croatian human and machine translations. The aim is to shed light on the differences in the way these structurally different languages make use of discourse information and provide insights for discourse-aware machine translation system development. The phenomena are automatically identified in parallel data using annotation produced by parsers and word alignment tools, enabling us to pinpoint patterns of interest in both languages. We make the analysis more fine-grained by including three corpora pertaining to three different registers. In a second step, we create a test set with the challenging linguistic constructions and use it to evaluate the performance of three MT systems. We show that both SMT and NMT systems struggle with handling these discourse phenomena, even though NMT tends to perform somewhat better than SMT. By providing an overview of patterns frequently occurring in actual language use, as well as by pointing out the weaknesses of current MT systems that commonly mistranslate them, we hope to contribute to the effort of resolving the issue of discourse phenomena in MT applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sostaric-etal-2018-discourse">
<titleInfo>
<title>Discourse-Related Language Contrasts in English-Croatian Human and Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Margita</namePart>
<namePart type="family">Šoštarić</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">Sara</namePart>
<namePart type="family">Stymne</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: Research 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">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an analysis of a number of coreference phenomena in English-Croatian human and machine translations. The aim is to shed light on the differences in the way these structurally different languages make use of discourse information and provide insights for discourse-aware machine translation system development. The phenomena are automatically identified in parallel data using annotation produced by parsers and word alignment tools, enabling us to pinpoint patterns of interest in both languages. We make the analysis more fine-grained by including three corpora pertaining to three different registers. In a second step, we create a test set with the challenging linguistic constructions and use it to evaluate the performance of three MT systems. We show that both SMT and NMT systems struggle with handling these discourse phenomena, even though NMT tends to perform somewhat better than SMT. By providing an overview of patterns frequently occurring in actual language use, as well as by pointing out the weaknesses of current MT systems that commonly mistranslate them, we hope to contribute to the effort of resolving the issue of discourse phenomena in MT applications.</abstract>
<identifier type="citekey">sostaric-etal-2018-discourse</identifier>
<identifier type="doi">10.18653/v1/W18-6305</identifier>
<location>
<url>https://aclanthology.org/W18-6305</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>36</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discourse-Related Language Contrasts in English-Croatian Human and Machine Translation
%A Šoštarić, Margita
%A Hardmeier, Christian
%A Stymne, Sara
%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: Research Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F sostaric-etal-2018-discourse
%X We present an analysis of a number of coreference phenomena in English-Croatian human and machine translations. The aim is to shed light on the differences in the way these structurally different languages make use of discourse information and provide insights for discourse-aware machine translation system development. The phenomena are automatically identified in parallel data using annotation produced by parsers and word alignment tools, enabling us to pinpoint patterns of interest in both languages. We make the analysis more fine-grained by including three corpora pertaining to three different registers. In a second step, we create a test set with the challenging linguistic constructions and use it to evaluate the performance of three MT systems. We show that both SMT and NMT systems struggle with handling these discourse phenomena, even though NMT tends to perform somewhat better than SMT. By providing an overview of patterns frequently occurring in actual language use, as well as by pointing out the weaknesses of current MT systems that commonly mistranslate them, we hope to contribute to the effort of resolving the issue of discourse phenomena in MT applications.
%R 10.18653/v1/W18-6305
%U https://aclanthology.org/W18-6305
%U https://doi.org/10.18653/v1/W18-6305
%P 36-48
Markdown (Informal)
[Discourse-Related Language Contrasts in English-Croatian Human and Machine Translation](https://aclanthology.org/W18-6305) (Šoštarić et al., WMT 2018)
ACL