@inproceedings{song-xu-2024-deep,
title = "A Deep Analysis of the Impact of Multiword Expressions and Named Entities on {C}hinese-{E}nglish Machine Translations",
author = "Song, Huacheng and
Xu, Hongzhi",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.357/",
doi = "10.18653/v1/2024.findings-emnlp.357",
pages = "6154--6165",
abstract = "In this paper, we present a study on the impact of so-called multiword expressions (MWEs) and multiword named entities (NEs) on the performance of Chinese-English machine translation (MT) systems. Built on an extended version of the data from the WMT22 Metrics Shared Task (with extra labels of 9 types of Chinese MWEs, and 19 types of Chinese multiword NEs) which includes scores and error annotations provided by human experts, we make further extraction of MWE- and NE-related translation errors. By investigating the human evaluation scores and the error rates on each category of MWEs and NEs, we find that: 1) MT systems tend to perform significantly worse on Chinese sentences with most kinds of MWEs and NEs; 2) MWEs and NEs which make up of about twenty percent of tokens, i.e. characters in Chinese, result in one-third of translation errors; 3) for 13 categories of MWEs and NEs, the error rates exceed 50{\%} with the highest to be 84.8{\%}. Based on the results, we emphasize that MWEs and NEs are still a bottleneck issue for MT and special attention to MWEs and NEs should be paid to further improving the performance of MT systems."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-xu-2024-deep">
<titleInfo>
<title>A Deep Analysis of the Impact of Multiword Expressions and Named Entities on Chinese-English Machine Translations</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>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</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>In this paper, we present a study on the impact of so-called multiword expressions (MWEs) and multiword named entities (NEs) on the performance of Chinese-English machine translation (MT) systems. Built on an extended version of the data from the WMT22 Metrics Shared Task (with extra labels of 9 types of Chinese MWEs, and 19 types of Chinese multiword NEs) which includes scores and error annotations provided by human experts, we make further extraction of MWE- and NE-related translation errors. By investigating the human evaluation scores and the error rates on each category of MWEs and NEs, we find that: 1) MT systems tend to perform significantly worse on Chinese sentences with most kinds of MWEs and NEs; 2) MWEs and NEs which make up of about twenty percent of tokens, i.e. characters in Chinese, result in one-third of translation errors; 3) for 13 categories of MWEs and NEs, the error rates exceed 50% with the highest to be 84.8%. Based on the results, we emphasize that MWEs and NEs are still a bottleneck issue for MT and special attention to MWEs and NEs should be paid to further improving the performance of MT systems.</abstract>
<identifier type="citekey">song-xu-2024-deep</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.357</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.357/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>6154</start>
<end>6165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Deep Analysis of the Impact of Multiword Expressions and Named Entities on Chinese-English Machine Translations
%A Song, Huacheng
%A Xu, Hongzhi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F song-xu-2024-deep
%X In this paper, we present a study on the impact of so-called multiword expressions (MWEs) and multiword named entities (NEs) on the performance of Chinese-English machine translation (MT) systems. Built on an extended version of the data from the WMT22 Metrics Shared Task (with extra labels of 9 types of Chinese MWEs, and 19 types of Chinese multiword NEs) which includes scores and error annotations provided by human experts, we make further extraction of MWE- and NE-related translation errors. By investigating the human evaluation scores and the error rates on each category of MWEs and NEs, we find that: 1) MT systems tend to perform significantly worse on Chinese sentences with most kinds of MWEs and NEs; 2) MWEs and NEs which make up of about twenty percent of tokens, i.e. characters in Chinese, result in one-third of translation errors; 3) for 13 categories of MWEs and NEs, the error rates exceed 50% with the highest to be 84.8%. Based on the results, we emphasize that MWEs and NEs are still a bottleneck issue for MT and special attention to MWEs and NEs should be paid to further improving the performance of MT systems.
%R 10.18653/v1/2024.findings-emnlp.357
%U https://aclanthology.org/2024.findings-emnlp.357/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.357
%P 6154-6165
Markdown (Informal)
[A Deep Analysis of the Impact of Multiword Expressions and Named Entities on Chinese-English Machine Translations](https://aclanthology.org/2024.findings-emnlp.357/) (Song & Xu, Findings 2024)
ACL