@inproceedings{raunak-etal-2024-slide,
title = "{SLIDE}: Reference-free Evaluation for Machine Translation using a Sliding Document Window",
author = "Raunak, Vikas and
Kocmi, Tom and
Post, Matt",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.18",
doi = "10.18653/v1/2024.naacl-short.18",
pages = "205--211",
abstract = "Reference-based metrics that operate at the sentence-level typically outperform quality estimation metrics, which have access only to the source and system output.This is unsurprising, since references resolve ambiguities that may be present in the source.In this paper, we investigate whether additional source context can effectively substitute for a reference.We present a metric named SLIDE (SLIding Document Evaluator), which operates on blocks of sentences. SLIDE leverages a moving window that slides over each document in the test set, feeding each chunk of sentences into an unmodified, off-the-shelf quality estimation model.We find that SLIDE obtains significantly higher pairwise system accuracy than its sentence-level baseline, in some cases even eliminating the gap with reference-base metrics.This suggests that source context may provide the same information as a human reference in disambiguating source ambiguities. This finding is especially pertinent for reference-free document-level evaluation, wherein SLIDE could provide higher-quality pairwise system assessments while only requiring document boundary annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raunak-etal-2024-slide">
<titleInfo>
<title>SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vikas</namePart>
<namePart type="family">Raunak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reference-based metrics that operate at the sentence-level typically outperform quality estimation metrics, which have access only to the source and system output.This is unsurprising, since references resolve ambiguities that may be present in the source.In this paper, we investigate whether additional source context can effectively substitute for a reference.We present a metric named SLIDE (SLIding Document Evaluator), which operates on blocks of sentences. SLIDE leverages a moving window that slides over each document in the test set, feeding each chunk of sentences into an unmodified, off-the-shelf quality estimation model.We find that SLIDE obtains significantly higher pairwise system accuracy than its sentence-level baseline, in some cases even eliminating the gap with reference-base metrics.This suggests that source context may provide the same information as a human reference in disambiguating source ambiguities. This finding is especially pertinent for reference-free document-level evaluation, wherein SLIDE could provide higher-quality pairwise system assessments while only requiring document boundary annotations.</abstract>
<identifier type="citekey">raunak-etal-2024-slide</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-short.18</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.18</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>205</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window
%A Raunak, Vikas
%A Kocmi, Tom
%A Post, Matt
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F raunak-etal-2024-slide
%X Reference-based metrics that operate at the sentence-level typically outperform quality estimation metrics, which have access only to the source and system output.This is unsurprising, since references resolve ambiguities that may be present in the source.In this paper, we investigate whether additional source context can effectively substitute for a reference.We present a metric named SLIDE (SLIding Document Evaluator), which operates on blocks of sentences. SLIDE leverages a moving window that slides over each document in the test set, feeding each chunk of sentences into an unmodified, off-the-shelf quality estimation model.We find that SLIDE obtains significantly higher pairwise system accuracy than its sentence-level baseline, in some cases even eliminating the gap with reference-base metrics.This suggests that source context may provide the same information as a human reference in disambiguating source ambiguities. This finding is especially pertinent for reference-free document-level evaluation, wherein SLIDE could provide higher-quality pairwise system assessments while only requiring document boundary annotations.
%R 10.18653/v1/2024.naacl-short.18
%U https://aclanthology.org/2024.naacl-short.18
%U https://doi.org/10.18653/v1/2024.naacl-short.18
%P 205-211
Markdown (Informal)
[SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window](https://aclanthology.org/2024.naacl-short.18) (Raunak et al., NAACL 2024)
ACL