@inproceedings{gutierrez-fandino-etal-2025-cost,
title = "Cost-Effective {E}-Commerce Catalog Translation at Scale Ensuring Named Entity Protection",
author = "Guti{\'e}rrez-Fandi{\~n}o, Asier and
Yero Salazar, Jorge and
Ruin, Clement and
Quintero-Roba, Alejandro and
Ravichandran, Shangeetha and
Perez-Martin, Jesus and
Adsul, Pankaj and
Garg, Suruchi and
Lezcano, Leonardo",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.81/",
pages = "1148--1157",
ISBN = "979-8-89176-333-3",
abstract = "We present an enterprise-grade translation platform for global e-commerce that combines daily batch and real-time API pipelines with optimized T5-based models and a Reference Generator to enforce {\ensuremath{>}}99{\%} non-translatable entity preservation. A linguist-driven rule engine and explainable evaluation framework (BLEU, COMET, and a custom e-commerce metric) enable continuous quality improvements. Deployed on GPU-accelerated inference servers and CPU-based processing nodes, our system processes millions of listings per day with sub-second latency and achieves 10{\texttimes}{--}100{\texttimes} cost savings over general-purpose LLMs for English{\textrightarrow}Spanish and English{\textrightarrow}French translation, all while version-tracking every update for robust enterprise rollouts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gutierrez-fandino-etal-2025-cost">
<titleInfo>
<title>Cost-Effective E-Commerce Catalog Translation at Scale Ensuring Named Entity Protection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asier</namePart>
<namePart type="family">Gutiérrez-Fandiño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Yero Salazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clement</namePart>
<namePart type="family">Ruin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Quintero-Roba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shangeetha</namePart>
<namePart type="family">Ravichandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesus</namePart>
<namePart type="family">Perez-Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pankaj</namePart>
<namePart type="family">Adsul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suruchi</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Lezcano</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 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</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">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>We present an enterprise-grade translation platform for global e-commerce that combines daily batch and real-time API pipelines with optimized T5-based models and a Reference Generator to enforce \ensuremath>99% non-translatable entity preservation. A linguist-driven rule engine and explainable evaluation framework (BLEU, COMET, and a custom e-commerce metric) enable continuous quality improvements. Deployed on GPU-accelerated inference servers and CPU-based processing nodes, our system processes millions of listings per day with sub-second latency and achieves 10×–100× cost savings over general-purpose LLMs for English→Spanish and English→French translation, all while version-tracking every update for robust enterprise rollouts.</abstract>
<identifier type="citekey">gutierrez-fandino-etal-2025-cost</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.81/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1148</start>
<end>1157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cost-Effective E-Commerce Catalog Translation at Scale Ensuring Named Entity Protection
%A Gutiérrez-Fandiño, Asier
%A Yero Salazar, Jorge
%A Ruin, Clement
%A Quintero-Roba, Alejandro
%A Ravichandran, Shangeetha
%A Perez-Martin, Jesus
%A Adsul, Pankaj
%A Garg, Suruchi
%A Lezcano, Leonardo
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F gutierrez-fandino-etal-2025-cost
%X We present an enterprise-grade translation platform for global e-commerce that combines daily batch and real-time API pipelines with optimized T5-based models and a Reference Generator to enforce \ensuremath>99% non-translatable entity preservation. A linguist-driven rule engine and explainable evaluation framework (BLEU, COMET, and a custom e-commerce metric) enable continuous quality improvements. Deployed on GPU-accelerated inference servers and CPU-based processing nodes, our system processes millions of listings per day with sub-second latency and achieves 10×–100× cost savings over general-purpose LLMs for English→Spanish and English→French translation, all while version-tracking every update for robust enterprise rollouts.
%U https://aclanthology.org/2025.emnlp-industry.81/
%P 1148-1157
Markdown (Informal)
[Cost-Effective E-Commerce Catalog Translation at Scale Ensuring Named Entity Protection](https://aclanthology.org/2025.emnlp-industry.81/) (Gutiérrez-Fandiño et al., EMNLP 2025)
ACL
- Asier Gutiérrez-Fandiño, Jorge Yero Salazar, Clement Ruin, Alejandro Quintero-Roba, Shangeetha Ravichandran, Jesus Perez-Martin, Pankaj Adsul, Suruchi Garg, and Leonardo Lezcano. 2025. Cost-Effective E-Commerce Catalog Translation at Scale Ensuring Named Entity Protection. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1148–1157, Suzhou (China). Association for Computational Linguistics.