@inproceedings{huang-etal-2026-hw-tscs,
title = "{HW}-{TSC}{'}s Submission to the {WMT}26 Terminology Translation Shared Task",
author = "Huang, Boqi and
Wei, Daimeng and
Guo, Jiaxin and
Luo, Yuanchang and
Shang, Hengchao and
Li, Zongyao and
Yang, Jinlong and
Wu, Zhanglin and
He, Yu and
Lan, Xiaoqing",
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.115/",
pages = "1801--1806",
ISBN = "979-8-89176-474-3",
abstract = "We describe HW-TSC{'}s submissions to both tracks and all language pairs of the WMT26 Terminology Translation Shared Task. Our primary system uses Qwen3.7-Max for source-term extraction, bilingual term alignment, and document translation. In Track 1, it matches the current document or translation chunk against the supplied dictionary and places at most 200 applicable term pairs in the translation prompt. In Track 2, it first induces a bilingual glossary from the seed bitexts and then reuses the Track 1 translation module. Induction combines open source-term extraction with seed-source expression matching, followed by LLM alignment to the seed targets. We optimize the extraction prompt with SkillOpt on a train/validation/test split of the WMT25 English{--}Chinese finance data and use Qwen3.7-Max to rewrite it for directions without labeled optimization data. Extraction recall rises from 0.6250 to 0.6344 on validation and from 0.6451 to 0.6674 on the held-out test split. On the same held-out test documents with Qwen3.7-Max, glossary induction raises TSR from 0.5212 (no glossary) to 0.7910 with the initial prompt and to 0.8026 after SkillOpt, with chrF++ of 57.45, 67.05, and 67.36; the official glossary yields TSR 0.9019 and chrF++ 63.94."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-hw-tscs">
<titleInfo>
<title>HW-TSC’s Submission to the WMT26 Terminology Translation Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanchang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Lan</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 describe HW-TSC’s submissions to both tracks and all language pairs of the WMT26 Terminology Translation Shared Task. Our primary system uses Qwen3.7-Max for source-term extraction, bilingual term alignment, and document translation. In Track 1, it matches the current document or translation chunk against the supplied dictionary and places at most 200 applicable term pairs in the translation prompt. In Track 2, it first induces a bilingual glossary from the seed bitexts and then reuses the Track 1 translation module. Induction combines open source-term extraction with seed-source expression matching, followed by LLM alignment to the seed targets. We optimize the extraction prompt with SkillOpt on a train/validation/test split of the WMT25 English–Chinese finance data and use Qwen3.7-Max to rewrite it for directions without labeled optimization data. Extraction recall rises from 0.6250 to 0.6344 on validation and from 0.6451 to 0.6674 on the held-out test split. On the same held-out test documents with Qwen3.7-Max, glossary induction raises TSR from 0.5212 (no glossary) to 0.7910 with the initial prompt and to 0.8026 after SkillOpt, with chrF++ of 57.45, 67.05, and 67.36; the official glossary yields TSR 0.9019 and chrF++ 63.94.</abstract>
<identifier type="citekey">huang-etal-2026-hw-tscs</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.115/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1801</start>
<end>1806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Submission to the WMT26 Terminology Translation Shared Task
%A Huang, Boqi
%A Wei, Daimeng
%A Guo, Jiaxin
%A Luo, Yuanchang
%A Shang, Hengchao
%A Li, Zongyao
%A Yang, Jinlong
%A Wu, Zhanglin
%A He, Yu
%A Lan, Xiaoqing
%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 huang-etal-2026-hw-tscs
%X We describe HW-TSC’s submissions to both tracks and all language pairs of the WMT26 Terminology Translation Shared Task. Our primary system uses Qwen3.7-Max for source-term extraction, bilingual term alignment, and document translation. In Track 1, it matches the current document or translation chunk against the supplied dictionary and places at most 200 applicable term pairs in the translation prompt. In Track 2, it first induces a bilingual glossary from the seed bitexts and then reuses the Track 1 translation module. Induction combines open source-term extraction with seed-source expression matching, followed by LLM alignment to the seed targets. We optimize the extraction prompt with SkillOpt on a train/validation/test split of the WMT25 English–Chinese finance data and use Qwen3.7-Max to rewrite it for directions without labeled optimization data. Extraction recall rises from 0.6250 to 0.6344 on validation and from 0.6451 to 0.6674 on the held-out test split. On the same held-out test documents with Qwen3.7-Max, glossary induction raises TSR from 0.5212 (no glossary) to 0.7910 with the initial prompt and to 0.8026 after SkillOpt, with chrF++ of 57.45, 67.05, and 67.36; the official glossary yields TSR 0.9019 and chrF++ 63.94.
%U https://aclanthology.org/2026.wmt-main.115/
%P 1801-1806
Markdown (Informal)
[HW-TSC’s Submission to the WMT26 Terminology Translation Shared Task](https://aclanthology.org/2026.wmt-main.115/) (Huang et al., WMT 2026)
ACL
- Boqi Huang, Daimeng Wei, Jiaxin Guo, Yuanchang Luo, Hengchao Shang, Zongyao Li, Jinlong Yang, Zhanglin Wu, Yu He, and Xiaoqing Lan. 2026. HW-TSC’s Submission to the WMT26 Terminology Translation Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1801–1806, Budapest, Hungary. Association for Computational Linguistics.