@inproceedings{li-zheng-2026-findings,
title = "Findings of the {WMT}26 Video Subtitle Translation Shared Task: Context and Candidate Selection Matter",
author = "Li, Zheng and
Zheng, Mao",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.58/",
pages = "1169--1179",
ISBN = "979-8-89176-474-3",
abstract = "We present the setup, systems, evaluation, and findings of the WMT26 Video Subtitle Translation shared task. The task covers translation from Simplified Chinese into English, Thai, Indonesian, Malay, and Traditional Chinese for Taiwan, China. Eight teams submitted 2,200 SRT files across 22 team-language combinations. We evaluated 2,198 unique team-language-video units with repeated LLM-based language quality assessment followed by human checking and correction. Each video was assessed three times, with valid positive scores aggregated by the median. ReopenAI led all five directions and achieved a macro-average of 89.357; laniqo ranked second with 78.265. Corrected scores were extractable from 93.36{\textbackslash}{\%} of the evaluation units, and 15.30{\textbackslash}{\%} of those scores differed from the automatic scores. Stronger results were associated with contextual prompting, diverse candidate generation, constrained selection, translator-critic specialization, terminology control, and deterministic subtitle validation. These cross-system associations are not controlled ablation evidence. Persistent challenges include cross-cue reference resolution, cultural and register adaptation, multilingual judge calibration, and balancing brevity with semantic completeness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-zheng-2026-findings">
<titleInfo>
<title>Findings of the WMT26 Video Subtitle Translation Shared Task: Context and Candidate Selection Matter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh 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">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>We present the setup, systems, evaluation, and findings of the WMT26 Video Subtitle Translation shared task. The task covers translation from Simplified Chinese into English, Thai, Indonesian, Malay, and Traditional Chinese for Taiwan, China. Eight teams submitted 2,200 SRT files across 22 team-language combinations. We evaluated 2,198 unique team-language-video units with repeated LLM-based language quality assessment followed by human checking and correction. Each video was assessed three times, with valid positive scores aggregated by the median. ReopenAI led all five directions and achieved a macro-average of 89.357; laniqo ranked second with 78.265. Corrected scores were extractable from 93.36\textbackslash% of the evaluation units, and 15.30\textbackslash% of those scores differed from the automatic scores. Stronger results were associated with contextual prompting, diverse candidate generation, constrained selection, translator-critic specialization, terminology control, and deterministic subtitle validation. These cross-system associations are not controlled ablation evidence. Persistent challenges include cross-cue reference resolution, cultural and register adaptation, multilingual judge calibration, and balancing brevity with semantic completeness.</abstract>
<identifier type="citekey">li-zheng-2026-findings</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.58/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1169</start>
<end>1179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the WMT26 Video Subtitle Translation Shared Task: Context and Candidate Selection Matter
%A Li, Zheng
%A Zheng, Mao
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F li-zheng-2026-findings
%X We present the setup, systems, evaluation, and findings of the WMT26 Video Subtitle Translation shared task. The task covers translation from Simplified Chinese into English, Thai, Indonesian, Malay, and Traditional Chinese for Taiwan, China. Eight teams submitted 2,200 SRT files across 22 team-language combinations. We evaluated 2,198 unique team-language-video units with repeated LLM-based language quality assessment followed by human checking and correction. Each video was assessed three times, with valid positive scores aggregated by the median. ReopenAI led all five directions and achieved a macro-average of 89.357; laniqo ranked second with 78.265. Corrected scores were extractable from 93.36\textbackslash% of the evaluation units, and 15.30\textbackslash% of those scores differed from the automatic scores. Stronger results were associated with contextual prompting, diverse candidate generation, constrained selection, translator-critic specialization, terminology control, and deterministic subtitle validation. These cross-system associations are not controlled ablation evidence. Persistent challenges include cross-cue reference resolution, cultural and register adaptation, multilingual judge calibration, and balancing brevity with semantic completeness.
%U https://aclanthology.org/2026.wmt-main.58/
%P 1169-1179
Markdown (Informal)
[Findings of the WMT26 Video Subtitle Translation Shared Task: Context and Candidate Selection Matter](https://aclanthology.org/2026.wmt-main.58/) (Li & Zheng, WMT 2026)
ACL