@inproceedings{raunak-etal-2023-evaluating,
title = "Evaluating Metrics for Document-context Evaluation in Machine Translation",
author = "Raunak, Vikas and
Kocmi, Tom and
Post, Matt",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.68",
doi = "10.18653/v1/2023.wmt-1.68",
pages = "812--814",
abstract = "We describe our submission of a new metric, SLIDE (Raunak et al., 2023), to the WMT 2023 metrics task. SLIDE is a reference-free quality-estimation metric that works by constructing a fixed sentence-length window over the documents in a test set, concatenating chunks and then sending them for scoring as a single unit by COMET (Rei et al, 2022). We find that SLIDE improves dramatically over its context-less counterpart on the two WMT22 evaluation campaigns (MQM and DA+SQM).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raunak-etal-2023-evaluating">
<titleInfo>
<title>Evaluating Metrics for Document-context Evaluation in Machine Translation</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>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<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">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">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">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe our submission of a new metric, SLIDE (Raunak et al., 2023), to the WMT 2023 metrics task. SLIDE is a reference-free quality-estimation metric that works by constructing a fixed sentence-length window over the documents in a test set, concatenating chunks and then sending them for scoring as a single unit by COMET (Rei et al, 2022). We find that SLIDE improves dramatically over its context-less counterpart on the two WMT22 evaluation campaigns (MQM and DA+SQM).</abstract>
<identifier type="citekey">raunak-etal-2023-evaluating</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.68</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.68</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>812</start>
<end>814</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Metrics for Document-context Evaluation in Machine Translation
%A Raunak, Vikas
%A Kocmi, Tom
%A Post, Matt
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F raunak-etal-2023-evaluating
%X We describe our submission of a new metric, SLIDE (Raunak et al., 2023), to the WMT 2023 metrics task. SLIDE is a reference-free quality-estimation metric that works by constructing a fixed sentence-length window over the documents in a test set, concatenating chunks and then sending them for scoring as a single unit by COMET (Rei et al, 2022). We find that SLIDE improves dramatically over its context-less counterpart on the two WMT22 evaluation campaigns (MQM and DA+SQM).
%R 10.18653/v1/2023.wmt-1.68
%U https://aclanthology.org/2023.wmt-1.68
%U https://doi.org/10.18653/v1/2023.wmt-1.68
%P 812-814
Markdown (Informal)
[Evaluating Metrics for Document-context Evaluation in Machine Translation](https://aclanthology.org/2023.wmt-1.68) (Raunak et al., WMT 2023)
ACL