@inproceedings{liu-etal-2025-toward,
title = "Toward Global {AI} Inclusivity: A Large-Scale Multilingual Terminology Dataset ({GIST})",
author = "Liu, Jiarui and
Ouzzani, Iman and
Li, Wenkai and
Zhang, Lechen and
Ou, Tianyue and
Bouamor, Houda and
Jin, Zhijing and
Diab, Mona T.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1148/",
doi = "10.18653/v1/2025.findings-acl.1148",
pages = "22327--22360",
ISBN = "979-8-89176-256-5",
abstract = "The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. This work introduces GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms were translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset{'}s quality was benchmarked against existing resources, demonstrating superior translation accuracy through crowdsourced evaluation. GIST was integrated into translation workflows using post-translation refinement methods that required no retraining, where LLM prompting consistently improved BLEU and COMET scores. A web demonstration on the ACL Anthology platform highlights its practical application, showcasing improved accessibility for non-English speakers. We address a critical gap in AI terminology resources and fosters global inclusivity and collaboration in AI research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-toward">
<titleInfo>
<title>Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iman</namePart>
<namePart type="family">Ouzzani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenkai</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lechen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyue</namePart>
<namePart type="family">Ou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijing</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. This work introduces GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms were translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset’s quality was benchmarked against existing resources, demonstrating superior translation accuracy through crowdsourced evaluation. GIST was integrated into translation workflows using post-translation refinement methods that required no retraining, where LLM prompting consistently improved BLEU and COMET scores. A web demonstration on the ACL Anthology platform highlights its practical application, showcasing improved accessibility for non-English speakers. We address a critical gap in AI terminology resources and fosters global inclusivity and collaboration in AI research.</abstract>
<identifier type="citekey">liu-etal-2025-toward</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1148</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1148/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22327</start>
<end>22360</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)
%A Liu, Jiarui
%A Ouzzani, Iman
%A Li, Wenkai
%A Zhang, Lechen
%A Ou, Tianyue
%A Bouamor, Houda
%A Jin, Zhijing
%A Diab, Mona T.
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F liu-etal-2025-toward
%X The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. This work introduces GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms were translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset’s quality was benchmarked against existing resources, demonstrating superior translation accuracy through crowdsourced evaluation. GIST was integrated into translation workflows using post-translation refinement methods that required no retraining, where LLM prompting consistently improved BLEU and COMET scores. A web demonstration on the ACL Anthology platform highlights its practical application, showcasing improved accessibility for non-English speakers. We address a critical gap in AI terminology resources and fosters global inclusivity and collaboration in AI research.
%R 10.18653/v1/2025.findings-acl.1148
%U https://aclanthology.org/2025.findings-acl.1148/
%U https://doi.org/10.18653/v1/2025.findings-acl.1148
%P 22327-22360
Markdown (Informal)
[Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)](https://aclanthology.org/2025.findings-acl.1148/) (Liu et al., Findings 2025)
ACL
- Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, and Mona T. Diab. 2025. Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST). In Findings of the Association for Computational Linguistics: ACL 2025, pages 22327–22360, Vienna, Austria. Association for Computational Linguistics.