@inproceedings{mukherjee-shrivastava-2024-chrf,
title = "chr{F}-{S}: Semantics Is All You Need",
author = "Mukherjee, Ananya and
Shrivastava, Manish",
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-1.33",
pages = "470--474",
abstract = "Machine translation (MT) evaluation metrics like BLEU and chrF++ are widely used reference-based metrics that do not require training and are language-independent. However, these metrics primarily focus on n-gram matching and often overlook semantic depth and contextual understanding. To address this gap, we introduce chrF-S (Semantic chrF++), an enhanced metric that integrates sentence embeddings to evaluate translation quality more comprehensively. By combining traditional character and word n-gram analysis with semantic information derived from embeddings, chrF-S captures both syntactic accuracy and sentence-level semantics. This paper presents our contributions to the WMT24 shared metrics task, showcasing our participation and the development of chrF-S. We also demonstrate that, according to preliminary results on the leaderboard, our metric performs on par with other supervised and LLM-based metrics. By merging semantic insights with n-gram precision, chrF-S offers a significant enhancement in the assessment of machine-generated translations, advancing the field of MT evaluation. Our code and data will be made available at \url{https://github.com/AnanyaCoder/chrF-S}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukherjee-shrivastava-2024-chrf">
<titleInfo>
<title>chrF-S: Semantics Is All You Need</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</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 metrics like BLEU and chrF++ are widely used reference-based metrics that do not require training and are language-independent. However, these metrics primarily focus on n-gram matching and often overlook semantic depth and contextual understanding. To address this gap, we introduce chrF-S (Semantic chrF++), an enhanced metric that integrates sentence embeddings to evaluate translation quality more comprehensively. By combining traditional character and word n-gram analysis with semantic information derived from embeddings, chrF-S captures both syntactic accuracy and sentence-level semantics. This paper presents our contributions to the WMT24 shared metrics task, showcasing our participation and the development of chrF-S. We also demonstrate that, according to preliminary results on the leaderboard, our metric performs on par with other supervised and LLM-based metrics. By merging semantic insights with n-gram precision, chrF-S offers a significant enhancement in the assessment of machine-generated translations, advancing the field of MT evaluation. Our code and data will be made available at https://github.com/AnanyaCoder/chrF-S.</abstract>
<identifier type="citekey">mukherjee-shrivastava-2024-chrf</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.33</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>470</start>
<end>474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T chrF-S: Semantics Is All You Need
%A Mukherjee, Ananya
%A Shrivastava, Manish
%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 mukherjee-shrivastava-2024-chrf
%X Machine translation (MT) evaluation metrics like BLEU and chrF++ are widely used reference-based metrics that do not require training and are language-independent. However, these metrics primarily focus on n-gram matching and often overlook semantic depth and contextual understanding. To address this gap, we introduce chrF-S (Semantic chrF++), an enhanced metric that integrates sentence embeddings to evaluate translation quality more comprehensively. By combining traditional character and word n-gram analysis with semantic information derived from embeddings, chrF-S captures both syntactic accuracy and sentence-level semantics. This paper presents our contributions to the WMT24 shared metrics task, showcasing our participation and the development of chrF-S. We also demonstrate that, according to preliminary results on the leaderboard, our metric performs on par with other supervised and LLM-based metrics. By merging semantic insights with n-gram precision, chrF-S offers a significant enhancement in the assessment of machine-generated translations, advancing the field of MT evaluation. Our code and data will be made available at https://github.com/AnanyaCoder/chrF-S.
%U https://aclanthology.org/2024.wmt-1.33
%P 470-474
Markdown (Informal)
[chrF-S: Semantics Is All You Need](https://aclanthology.org/2024.wmt-1.33) (Mukherjee & Shrivastava, WMT 2024)
ACL
- Ananya Mukherjee and Manish Shrivastava. 2024. chrF-S: Semantics Is All You Need. In Proceedings of the Ninth Conference on Machine Translation, pages 470–474, Miami, Florida, USA. Association for Computational Linguistics.