@inproceedings{song-xu-2024-benchmarking,
title = "Benchmarking the Performance of Machine Translation Evaluation Metrics with {C}hinese Multiword Expressions",
author = "Song, Huacheng and
Xu, Hongzhi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.198",
pages = "2204--2216",
abstract = "To investigate the impact of Multiword Expressions (MWEs) on the fine-grained performance of the state-of-the-art metrics for Machine Translation Evaluation (MTE), we conduct experiments on the WMT22 Metrics Shared Task dataset with a preliminary focus on the Chinese-to-English language pair. We further annotate 28 types of Chinese MWEs on the source texts and then examine the performance of 31 MTE metrics on groups of sentences containing different MWEs. We have 3 interesting findings: 1) Machine Translation (MT) systems tend to perform worse on most Chinese MWE categories, confirming the previous claim that MWEs are a bottleneck of MT; 2) automatic metrics tend to overrate the translation of sentences containing MWEs; 3) most neural-network-based metrics perform better than string-overlap-based metrics. It concludes that both MT systems and MTE metrics still suffer from MWEs, suggesting richer annotation of data to facilitate MWE-aware automatic MTE and MT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-xu-2024-benchmarking">
<titleInfo>
<title>Benchmarking the Performance of Machine Translation Evaluation Metrics with Chinese Multiword Expressions</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">Hongzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To investigate the impact of Multiword Expressions (MWEs) on the fine-grained performance of the state-of-the-art metrics for Machine Translation Evaluation (MTE), we conduct experiments on the WMT22 Metrics Shared Task dataset with a preliminary focus on the Chinese-to-English language pair. We further annotate 28 types of Chinese MWEs on the source texts and then examine the performance of 31 MTE metrics on groups of sentences containing different MWEs. We have 3 interesting findings: 1) Machine Translation (MT) systems tend to perform worse on most Chinese MWE categories, confirming the previous claim that MWEs are a bottleneck of MT; 2) automatic metrics tend to overrate the translation of sentences containing MWEs; 3) most neural-network-based metrics perform better than string-overlap-based metrics. It concludes that both MT systems and MTE metrics still suffer from MWEs, suggesting richer annotation of data to facilitate MWE-aware automatic MTE and MT.</abstract>
<identifier type="citekey">song-xu-2024-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.198</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2204</start>
<end>2216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking the Performance of Machine Translation Evaluation Metrics with Chinese Multiword Expressions
%A Song, Huacheng
%A Xu, Hongzhi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F song-xu-2024-benchmarking
%X To investigate the impact of Multiword Expressions (MWEs) on the fine-grained performance of the state-of-the-art metrics for Machine Translation Evaluation (MTE), we conduct experiments on the WMT22 Metrics Shared Task dataset with a preliminary focus on the Chinese-to-English language pair. We further annotate 28 types of Chinese MWEs on the source texts and then examine the performance of 31 MTE metrics on groups of sentences containing different MWEs. We have 3 interesting findings: 1) Machine Translation (MT) systems tend to perform worse on most Chinese MWE categories, confirming the previous claim that MWEs are a bottleneck of MT; 2) automatic metrics tend to overrate the translation of sentences containing MWEs; 3) most neural-network-based metrics perform better than string-overlap-based metrics. It concludes that both MT systems and MTE metrics still suffer from MWEs, suggesting richer annotation of data to facilitate MWE-aware automatic MTE and MT.
%U https://aclanthology.org/2024.lrec-main.198
%P 2204-2216
Markdown (Informal)
[Benchmarking the Performance of Machine Translation Evaluation Metrics with Chinese Multiword Expressions](https://aclanthology.org/2024.lrec-main.198) (Song & Xu, LREC-COLING 2024)
ACL