@inproceedings{vojtechova-etal-2019-sao,
title = "{SAO} {WMT}19 Test Suite: Machine Translation of Audit Reports",
author = "Vojt{\v{e}}chov{\'a}, Tereza and
Nov{\'a}k, Michal and
Klou{\v{c}}ek, Milo{\v{s}} and
Bojar, Ond{\v{r}}ej",
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/W19-5355",
doi = "10.18653/v1/W19-5355",
pages = "481--493",
abstract = "This paper describes a machine translation test set of documents from the auditing domain and its use as one of the {``}test suites{''} in the WMT19 News Translation Task for translation directions involving Czech, English and German. Our evaluation suggests that current MT systems optimized for the general news domain can perform quite well even in the particular domain of audit reports. The detailed manual evaluation however indicates that deep factual knowledge of the domain is necessary. For the naked eye of a non-expert, translations by many systems seem almost perfect and automatic MT evaluation with one reference is practically useless for considering these details. Furthermore, we show on a sample document from the domain of agreements that even the best systems completely fail in preserving the semantics of the agreement, namely the identity of the parties.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vojtechova-etal-2019-sao">
<titleInfo>
<title>SAO WMT19 Test Suite: Machine Translation of Audit Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tereza</namePart>
<namePart type="family">Vojtěchová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloš</namePart>
<namePart type="family">Klouček</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>
<originInfo>
<dateIssued>2019-aug</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>
<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 describes a machine translation test set of documents from the auditing domain and its use as one of the “test suites” in the WMT19 News Translation Task for translation directions involving Czech, English and German. Our evaluation suggests that current MT systems optimized for the general news domain can perform quite well even in the particular domain of audit reports. The detailed manual evaluation however indicates that deep factual knowledge of the domain is necessary. For the naked eye of a non-expert, translations by many systems seem almost perfect and automatic MT evaluation with one reference is practically useless for considering these details. Furthermore, we show on a sample document from the domain of agreements that even the best systems completely fail in preserving the semantics of the agreement, namely the identity of the parties.</abstract>
<identifier type="citekey">vojtechova-etal-2019-sao</identifier>
<identifier type="doi">10.18653/v1/W19-5355</identifier>
<location>
<url>https://aclanthology.org/W19-5355</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>481</start>
<end>493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAO WMT19 Test Suite: Machine Translation of Audit Reports
%A Vojtěchová, Tereza
%A Novák, Michal
%A Klouček, Miloš
%A Bojar, Ondřej
%S Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F vojtechova-etal-2019-sao
%X This paper describes a machine translation test set of documents from the auditing domain and its use as one of the “test suites” in the WMT19 News Translation Task for translation directions involving Czech, English and German. Our evaluation suggests that current MT systems optimized for the general news domain can perform quite well even in the particular domain of audit reports. The detailed manual evaluation however indicates that deep factual knowledge of the domain is necessary. For the naked eye of a non-expert, translations by many systems seem almost perfect and automatic MT evaluation with one reference is practically useless for considering these details. Furthermore, we show on a sample document from the domain of agreements that even the best systems completely fail in preserving the semantics of the agreement, namely the identity of the parties.
%R 10.18653/v1/W19-5355
%U https://aclanthology.org/W19-5355
%U https://doi.org/10.18653/v1/W19-5355
%P 481-493
Markdown (Informal)
[SAO WMT19 Test Suite: Machine Translation of Audit Reports](https://aclanthology.org/W19-5355) (Vojtěchová et al., 2019)
ACL
- Tereza Vojtěchová, Michal Novák, Miloš Klouček, and Ondřej Bojar. 2019. SAO WMT19 Test Suite: Machine Translation of Audit Reports. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 481–493, Florence, Italy. Association for Computational Linguistics.