@inproceedings{maharjan-shrestha-2025-rankedcomet,
title = "{R}anked{COMET}: Elevating a 2022 Baseline to a Top-5 Finish in the {WMT} 2025 {QE} Task",
author = "Maharjan, Sujal and
Shrestha, Astha",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Tenth Conference on Machine Translation",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wmt-1.74/",
pages = "994--998",
ISBN = "979-8-89176-341-8",
abstract = "This paper presents rankedCOMET, a lightweight per-language-pair calibration applied to the publicly available Unbabel/wmt22-comet-da model that yields a competitive Quality Estimation (QE) system for the WMT 2025 shared task. This approach transforms raw model outputs into per-language average ranks and min{--}max normalizes those ranks to [0,1], maintaining intra-language ordering while generating consistent numeric ranges across language pairs. Applied to 742,740 test segments and submitted to Codabench, this unsupervised post-processing enhanced the aggregated Pearson correlation on the preliminary snapshot and led to a 5th-place finish. We provide detailed pseudocode, ablations (including a negative ensemble attempt), and a reproducible analysis pipeline providing Pearson, Spearman, and Kendall correlations with bootstrap confidence intervals."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maharjan-shrestha-2025-rankedcomet">
<titleInfo>
<title>RankedCOMET: Elevating a 2022 Baseline to a Top-5 Finish in the WMT 2025 QE Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sujal</namePart>
<namePart type="family">Maharjan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Astha</namePart>
<namePart type="family">Shrestha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-341-8</identifier>
</relatedItem>
<abstract>This paper presents rankedCOMET, a lightweight per-language-pair calibration applied to the publicly available Unbabel/wmt22-comet-da model that yields a competitive Quality Estimation (QE) system for the WMT 2025 shared task. This approach transforms raw model outputs into per-language average ranks and min–max normalizes those ranks to [0,1], maintaining intra-language ordering while generating consistent numeric ranges across language pairs. Applied to 742,740 test segments and submitted to Codabench, this unsupervised post-processing enhanced the aggregated Pearson correlation on the preliminary snapshot and led to a 5th-place finish. We provide detailed pseudocode, ablations (including a negative ensemble attempt), and a reproducible analysis pipeline providing Pearson, Spearman, and Kendall correlations with bootstrap confidence intervals.</abstract>
<identifier type="citekey">maharjan-shrestha-2025-rankedcomet</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.74/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>994</start>
<end>998</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RankedCOMET: Elevating a 2022 Baseline to a Top-5 Finish in the WMT 2025 QE Task
%A Maharjan, Sujal
%A Shrestha, Astha
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F maharjan-shrestha-2025-rankedcomet
%X This paper presents rankedCOMET, a lightweight per-language-pair calibration applied to the publicly available Unbabel/wmt22-comet-da model that yields a competitive Quality Estimation (QE) system for the WMT 2025 shared task. This approach transforms raw model outputs into per-language average ranks and min–max normalizes those ranks to [0,1], maintaining intra-language ordering while generating consistent numeric ranges across language pairs. Applied to 742,740 test segments and submitted to Codabench, this unsupervised post-processing enhanced the aggregated Pearson correlation on the preliminary snapshot and led to a 5th-place finish. We provide detailed pseudocode, ablations (including a negative ensemble attempt), and a reproducible analysis pipeline providing Pearson, Spearman, and Kendall correlations with bootstrap confidence intervals.
%U https://aclanthology.org/2025.wmt-1.74/
%P 994-998
Markdown (Informal)
[RankedCOMET: Elevating a 2022 Baseline to a Top-5 Finish in the WMT 2025 QE Task](https://aclanthology.org/2025.wmt-1.74/) (Maharjan & Shrestha, WMT 2025)
ACL