@inproceedings{bezancon-etal-2026-met,
title = "How {I} Met Your Snowclone: Unsupervised Discovery of Snowclone Patterns in Large Datasets",
author = {Bezan{\c{c}}on, Julien and
Lejeune, Ga{\"e}l and
Hernandez, Marceau},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.622/",
doi = "10.63317/5iuorx8jxpiw",
pages = "7829--7844",
abstract = "Snowclones are a type of Multiword Expression (MWE) pattern that includes open slots, i.e. positions that can be filled with various words. For example, in the phrase ``May the X be with you,'' the slot X can be replaced with virtually any noun. A key feature of snowclones is that the original MWE remains recognizable, carrying its meaning into the new form. However, previous work has not shown whether such substitutions are limited to fixed positions. In practice, variations such as ``May the force bee with you'' are also possible. In this paper, we propose to use Locality Sensitive Hashing (LSH) to automatically extract snowclone patterns from the non-commercial IMDb dataset. This process results in the creation of the FROST lexicon, comprising 29,011 pattern candidates and 991,626 snowclone candidates distributed in 29 languages. We then annotate 1,500 discovered patterns and 1,000 snowclones from the \textsc{FROST} lexicon to assess its quality. Our findings suggest that (i) most substitutions in snowclones occur at consistent positions and (ii) snowclones can be reliably discovered at scale using LSH and similarity-based metrics. This work provides the first large-scale lexicon of snowclone-based MWEs and a method that can support future research on MWEs and snowclones discovery."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bezancon-etal-2026-met">
<titleInfo>
<title>How I Met Your Snowclone: Unsupervised Discovery of Snowclone Patterns in Large Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Bezançon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaël</namePart>
<namePart type="family">Lejeune</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marceau</namePart>
<namePart type="family">Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Snowclones are a type of Multiword Expression (MWE) pattern that includes open slots, i.e. positions that can be filled with various words. For example, in the phrase “May the X be with you,” the slot X can be replaced with virtually any noun. A key feature of snowclones is that the original MWE remains recognizable, carrying its meaning into the new form. However, previous work has not shown whether such substitutions are limited to fixed positions. In practice, variations such as “May the force bee with you” are also possible. In this paper, we propose to use Locality Sensitive Hashing (LSH) to automatically extract snowclone patterns from the non-commercial IMDb dataset. This process results in the creation of the FROST lexicon, comprising 29,011 pattern candidates and 991,626 snowclone candidates distributed in 29 languages. We then annotate 1,500 discovered patterns and 1,000 snowclones from the FROST lexicon to assess its quality. Our findings suggest that (i) most substitutions in snowclones occur at consistent positions and (ii) snowclones can be reliably discovered at scale using LSH and similarity-based metrics. This work provides the first large-scale lexicon of snowclone-based MWEs and a method that can support future research on MWEs and snowclones discovery.</abstract>
<identifier type="citekey">bezancon-etal-2026-met</identifier>
<identifier type="doi">10.63317/5iuorx8jxpiw</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.622/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7829</start>
<end>7844</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How I Met Your Snowclone: Unsupervised Discovery of Snowclone Patterns in Large Datasets
%A Bezançon, Julien
%A Lejeune, Gaël
%A Hernandez, Marceau
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F bezancon-etal-2026-met
%X Snowclones are a type of Multiword Expression (MWE) pattern that includes open slots, i.e. positions that can be filled with various words. For example, in the phrase “May the X be with you,” the slot X can be replaced with virtually any noun. A key feature of snowclones is that the original MWE remains recognizable, carrying its meaning into the new form. However, previous work has not shown whether such substitutions are limited to fixed positions. In practice, variations such as “May the force bee with you” are also possible. In this paper, we propose to use Locality Sensitive Hashing (LSH) to automatically extract snowclone patterns from the non-commercial IMDb dataset. This process results in the creation of the FROST lexicon, comprising 29,011 pattern candidates and 991,626 snowclone candidates distributed in 29 languages. We then annotate 1,500 discovered patterns and 1,000 snowclones from the FROST lexicon to assess its quality. Our findings suggest that (i) most substitutions in snowclones occur at consistent positions and (ii) snowclones can be reliably discovered at scale using LSH and similarity-based metrics. This work provides the first large-scale lexicon of snowclone-based MWEs and a method that can support future research on MWEs and snowclones discovery.
%R 10.63317/5iuorx8jxpiw
%U https://aclanthology.org/2026.lrec-1.622/
%U https://doi.org/10.63317/5iuorx8jxpiw
%P 7829-7844
Markdown (Informal)
[How I Met Your Snowclone: Unsupervised Discovery of Snowclone Patterns in Large Datasets](https://aclanthology.org/2026.lrec-1.622/) (Bezançon et al., LREC 2026)
ACL