@inproceedings{kim-etal-2025-milq,
title = "{M}i{LQ}: Benchmarking {IR} Models for Bilingual Web Search with Mixed Language Queries",
author = "Kim, Jonghwi and
Kang, Deokhyung and
Hwang, Seonjeong and
Kim, Yunsu and
Ok, Jungseul and
Lee, Gary",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1153/",
doi = "10.18653/v1/2025.emnlp-main.1153",
pages = "22643--22659",
ISBN = "979-8-89176-332-6",
abstract = "Despite bilingual speakers frequently using mixed-language queries in web searches, Information Retrieval (IR) research on them remains scarce. To address this, we introduce ***MiLQ***, ***Mi***xed-***L***anguage ***Q***uery test set, the first public benchmark of mixed-language queries, qualified as realistic and relatively preferred. Experiments show that multilingual IR models perform moderately on MiLQ and inconsistently across native, English, and mixed-language queries, also suggesting code-switched training data{'}s potential for robust IR models handling such queries. Meanwhile, intentional English mixing in queries proves an effective strategy for bilinguals searching English documents, which our analysis attributes to enhanced token matching compared to native queries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-milq">
<titleInfo>
<title>MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonghwi</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deokhyung</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonjeong</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunsu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungseul</namePart>
<namePart type="family">Ok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gary</namePart>
<namePart type="family">Lee</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Despite bilingual speakers frequently using mixed-language queries in web searches, Information Retrieval (IR) research on them remains scarce. To address this, we introduce ***MiLQ***, ***Mi***xed-***L***anguage ***Q***uery test set, the first public benchmark of mixed-language queries, qualified as realistic and relatively preferred. Experiments show that multilingual IR models perform moderately on MiLQ and inconsistently across native, English, and mixed-language queries, also suggesting code-switched training data’s potential for robust IR models handling such queries. Meanwhile, intentional English mixing in queries proves an effective strategy for bilinguals searching English documents, which our analysis attributes to enhanced token matching compared to native queries.</abstract>
<identifier type="citekey">kim-etal-2025-milq</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1153</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1153/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>22643</start>
<end>22659</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries
%A Kim, Jonghwi
%A Kang, Deokhyung
%A Hwang, Seonjeong
%A Kim, Yunsu
%A Ok, Jungseul
%A Lee, Gary
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F kim-etal-2025-milq
%X Despite bilingual speakers frequently using mixed-language queries in web searches, Information Retrieval (IR) research on them remains scarce. To address this, we introduce ***MiLQ***, ***Mi***xed-***L***anguage ***Q***uery test set, the first public benchmark of mixed-language queries, qualified as realistic and relatively preferred. Experiments show that multilingual IR models perform moderately on MiLQ and inconsistently across native, English, and mixed-language queries, also suggesting code-switched training data’s potential for robust IR models handling such queries. Meanwhile, intentional English mixing in queries proves an effective strategy for bilinguals searching English documents, which our analysis attributes to enhanced token matching compared to native queries.
%R 10.18653/v1/2025.emnlp-main.1153
%U https://aclanthology.org/2025.emnlp-main.1153/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1153
%P 22643-22659
Markdown (Informal)
[MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries](https://aclanthology.org/2025.emnlp-main.1153/) (Kim et al., EMNLP 2025)
ACL