@inproceedings{neumannova-bojar-2023-role,
title = "The Role of Compounds in Human vs. Machine Translation Quality",
author = "Neumannova, Kristyna and
Bojar, Ond{\v{r}}ej",
editor = "Utiyama, Masao and
Wang, Rui",
booktitle = "Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track",
month = sep,
year = "2023",
address = "Macau SAR, China",
publisher = "Asia-Pacific Association for Machine Translation",
url = "https://aclanthology.org/2023.mtsummit-research.21",
pages = "248--260",
abstract = "We focus on the production of German compounds in English-to-German manual and automatic translation. On the example of WMT21 news translation test set, we observe that even the best MT systems produce much fewer compounds compared to three independent manual translations. Despite this striking difference, we observe that this insufficiency is not apparent in manual evaluation methods that target the overall translation quality (DA and MQM). Simple automatic methods like BLEU somewhat surprisingly provide a better indication of this quality aspect. Our manual analysis of system outputs, including our freshly trained Transformer models, confirms that current deep neural systems operating at the level of subword units are capable of constructing novel words, including novel compounds. This effect however cannot be measured using static dictionaries of compounds such as GermaNet. German compounds thus pose an interesting challenge for future development of MT systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="neumannova-bojar-2023-role">
<titleInfo>
<title>The Role of Compounds in Human vs. Machine Translation Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristyna</namePart>
<namePart type="family">Neumannova</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>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asia-Pacific Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Macau SAR, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We focus on the production of German compounds in English-to-German manual and automatic translation. On the example of WMT21 news translation test set, we observe that even the best MT systems produce much fewer compounds compared to three independent manual translations. Despite this striking difference, we observe that this insufficiency is not apparent in manual evaluation methods that target the overall translation quality (DA and MQM). Simple automatic methods like BLEU somewhat surprisingly provide a better indication of this quality aspect. Our manual analysis of system outputs, including our freshly trained Transformer models, confirms that current deep neural systems operating at the level of subword units are capable of constructing novel words, including novel compounds. This effect however cannot be measured using static dictionaries of compounds such as GermaNet. German compounds thus pose an interesting challenge for future development of MT systems.</abstract>
<identifier type="citekey">neumannova-bojar-2023-role</identifier>
<location>
<url>https://aclanthology.org/2023.mtsummit-research.21</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>248</start>
<end>260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Role of Compounds in Human vs. Machine Translation Quality
%A Neumannova, Kristyna
%A Bojar, Ondřej
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F neumannova-bojar-2023-role
%X We focus on the production of German compounds in English-to-German manual and automatic translation. On the example of WMT21 news translation test set, we observe that even the best MT systems produce much fewer compounds compared to three independent manual translations. Despite this striking difference, we observe that this insufficiency is not apparent in manual evaluation methods that target the overall translation quality (DA and MQM). Simple automatic methods like BLEU somewhat surprisingly provide a better indication of this quality aspect. Our manual analysis of system outputs, including our freshly trained Transformer models, confirms that current deep neural systems operating at the level of subword units are capable of constructing novel words, including novel compounds. This effect however cannot be measured using static dictionaries of compounds such as GermaNet. German compounds thus pose an interesting challenge for future development of MT systems.
%U https://aclanthology.org/2023.mtsummit-research.21
%P 248-260
Markdown (Informal)
[The Role of Compounds in Human vs. Machine Translation Quality](https://aclanthology.org/2023.mtsummit-research.21) (Neumannova & Bojar, MTSummit 2023)
ACL