@inproceedings{song-etal-2024-grammatical,
title = "How Grammatical Features Impact Machine Translation: A New Test Suite for {C}hinese-{E}nglish {MT} Evaluation",
author = "Song, Huacheng and
Li, Yi and
Wu, Yiwen and
Liu, Yu and
Lin, Jingxia and
Xu, Hongzhi",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.117",
pages = "1200--1221",
abstract = "Machine translation (MT) evaluation has evolved toward a trend of fine-grained granularity, enabling a more precise diagnosis of hidden flaws and weaknesses of MT systems from various perspectives. This paper examines how MT systems are potentially affected by certain grammatical features, offering insights into the challenges these features pose and suggesting possible directions for improvement. We develop a new test suite by extracting 7,848 sentences from a multi-domain Chinese-English parallel corpus. All the Chinese text was further annotated with 43 grammatical features using a semi-automatic method. This test suite was subsequently used to evaluate eight state-of-the-art MT systems according to six different automatic evaluation metrics. The results reveal intriguing patterns of MT performance associated with different domains and various grammatical features, highlighting the test suite{'}s effectiveness. The test suite was made publicly available and it will serve as an important benchmark for evaluating and diagnosing Chinese-English MT systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2024-grammatical">
<titleInfo>
<title>How Grammatical Features Impact Machine Translation: A New Test Suite for Chinese-English MT Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huacheng</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingxia</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<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">Tom</namePart>
<namePart type="family">Kocmi</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation (MT) evaluation has evolved toward a trend of fine-grained granularity, enabling a more precise diagnosis of hidden flaws and weaknesses of MT systems from various perspectives. This paper examines how MT systems are potentially affected by certain grammatical features, offering insights into the challenges these features pose and suggesting possible directions for improvement. We develop a new test suite by extracting 7,848 sentences from a multi-domain Chinese-English parallel corpus. All the Chinese text was further annotated with 43 grammatical features using a semi-automatic method. This test suite was subsequently used to evaluate eight state-of-the-art MT systems according to six different automatic evaluation metrics. The results reveal intriguing patterns of MT performance associated with different domains and various grammatical features, highlighting the test suite’s effectiveness. The test suite was made publicly available and it will serve as an important benchmark for evaluating and diagnosing Chinese-English MT systems.</abstract>
<identifier type="citekey">song-etal-2024-grammatical</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.117</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1200</start>
<end>1221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Grammatical Features Impact Machine Translation: A New Test Suite for Chinese-English MT Evaluation
%A Song, Huacheng
%A Li, Yi
%A Wu, Yiwen
%A Liu, Yu
%A Lin, Jingxia
%A Xu, Hongzhi
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F song-etal-2024-grammatical
%X Machine translation (MT) evaluation has evolved toward a trend of fine-grained granularity, enabling a more precise diagnosis of hidden flaws and weaknesses of MT systems from various perspectives. This paper examines how MT systems are potentially affected by certain grammatical features, offering insights into the challenges these features pose and suggesting possible directions for improvement. We develop a new test suite by extracting 7,848 sentences from a multi-domain Chinese-English parallel corpus. All the Chinese text was further annotated with 43 grammatical features using a semi-automatic method. This test suite was subsequently used to evaluate eight state-of-the-art MT systems according to six different automatic evaluation metrics. The results reveal intriguing patterns of MT performance associated with different domains and various grammatical features, highlighting the test suite’s effectiveness. The test suite was made publicly available and it will serve as an important benchmark for evaluating and diagnosing Chinese-English MT systems.
%U https://aclanthology.org/2024.wmt-1.117
%P 1200-1221
Markdown (Informal)
[How Grammatical Features Impact Machine Translation: A New Test Suite for Chinese-English MT Evaluation](https://aclanthology.org/2024.wmt-1.117) (Song et al., WMT 2024)
ACL