<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2026-synthetic">
    <titleInfo>
        <title>From Synthetic to Localized: Benchmarking Multilingual Intent Classification in Logistics Customer Service</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haoyu</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinyu</namePart>
        <namePart type="family">Zhuang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haoran</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shuhang</namePart>
        <namePart type="family">yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Han</namePart>
        <namePart type="family">Kunpeng</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Multilingual intent classification is central to logistics customer-service systems, where models must handle noisy user queries across languages and hierarchical labels. Yet many multilingual benchmarks rely on machine-translated text, which is cleaner than real customer requests and can overestimate robustness. We present a public benchmark for hierarchical multilingual intent classification from real logistics logs: approximately 30K de-identified, single-utterance queries curated from 600K records through filtering, LLM-assisted quality control, human privacy review, and sampled label auditing. The dataset uses a two-level taxonomy with 13 parent and 17 leaf intents; English, Spanish, and Arabic are seen languages, while Indonesian, Chinese, and Thai support zero-shot evaluation. To measure the gap between machine-translated and professionally localized evaluation, we provide paired test sets derived from the same source items. We benchmark multilingual encoders, embedding models, and small language models under flat and hierarchical protocols, and find that machine translation tests yield higher accuracy in most settings. [Prompts and sample data are available at \ensuremath&lt;https://github.com/JTExpress-MICCS/MICCS\ensuremath&gt;. A preprint version of this work is available at \ensuremath&lt;https://arxiv.org/abs/2603.23172\ensuremath&gt;.]</abstract>
    <identifier type="citekey">he-etal-2026-synthetic</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.121/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2078</start>
            <end>2092</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Synthetic to Localized: Benchmarking Multilingual Intent Classification in Logistics Customer Service
%A He, Haoyu
%A Zhuang, Jinyu
%A Chu, Haoran
%A yu, Shuhang
%A Wang, Hao
%A Kunpeng, Han
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F he-etal-2026-synthetic
%X Multilingual intent classification is central to logistics customer-service systems, where models must handle noisy user queries across languages and hierarchical labels. Yet many multilingual benchmarks rely on machine-translated text, which is cleaner than real customer requests and can overestimate robustness. We present a public benchmark for hierarchical multilingual intent classification from real logistics logs: approximately 30K de-identified, single-utterance queries curated from 600K records through filtering, LLM-assisted quality control, human privacy review, and sampled label auditing. The dataset uses a two-level taxonomy with 13 parent and 17 leaf intents; English, Spanish, and Arabic are seen languages, while Indonesian, Chinese, and Thai support zero-shot evaluation. To measure the gap between machine-translated and professionally localized evaluation, we provide paired test sets derived from the same source items. We benchmark multilingual encoders, embedding models, and small language models under flat and hierarchical protocols, and find that machine translation tests yield higher accuracy in most settings. [Prompts and sample data are available at \ensuremath<https://github.com/JTExpress-MICCS/MICCS\ensuremath>. A preprint version of this work is available at \ensuremath<https://arxiv.org/abs/2603.23172\ensuremath>.]
%U https://aclanthology.org/2026.emnlp-industry.121/
%P 2078-2092

Markdown (Informal)

[From Synthetic to Localized: Benchmarking Multilingual Intent Classification in Logistics Customer Service](https://aclanthology.org/2026.emnlp-industry.121/) (He et al., EMNLP 2026)

• From Synthetic to Localized: Benchmarking Multilingual Intent Classification in Logistics Customer Service (He et al., EMNLP 2026)

ACL

• Haoyu He, Jinyu Zhuang, Haoran Chu, Shuhang yu, Hao Wang, and Han Kunpeng. 2026. From Synthetic to Localized: Benchmarking Multilingual Intent Classification in Logistics Customer Service. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2078–2092, Budapest, Hungary. Association for Computational Linguistics.