@inproceedings{carp-2026-tiberiucarp,
title = "tiberiucarp at {MWE}-2026 {A}d{MIR}e 2: {GLIMMER}-Gloss-based Image Multiword Meaning Expression Ranker",
author = "Carp, Andrei Tiberiu",
editor = {Ojha, Atul Kr. and
Mititelu, Verginica Barbu and
Constant, Mathieu and
Stoyanova, Ivelina and
Do{\u{g}}ru{\"o}z, A. Seza and
Rademaker, Alexandre},
booktitle = "Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)",
month = mar,
year = "2026",
address = "Rabat, Marocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mwe-1.23/",
pages = "170--176",
ISBN = "979-8-89176-363-0",
abstract = "Multiword expressions (MWEs), particularlyidioms, pose persistent challengesfor vision-language systems due to theirnon-compositional semantics and culturallygrounded meanings. This paper presentsGLIMMER, a three-stage hybrid ranking systemthat evaluates how well images expressthe intended meaning of MWEs across 15 languages.Our approach uses LLM-generatedsemantic glosses as multilingual meaning anchors,combined with dual-path embeddingscoring (textual captions and visual features),and LLM-based semantic verification. Evaluatedon the ADMIRE shared task benchmark,GLIMMER achieves competitive performanceacross diverse languages without relying onparallel training data or language-specific resources.The results show that using glossesto anchor meaning helps match idioms withimages across languages and modalities, andthat combining retrieval with reasoning is morerobust than using embeddings alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carp-2026-tiberiucarp">
<titleInfo>
<title>tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="given">Tiberiu</namePart>
<namePart type="family">Carp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Stoyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Marocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-363-0</identifier>
</relatedItem>
<abstract>Multiword expressions (MWEs), particularlyidioms, pose persistent challengesfor vision-language systems due to theirnon-compositional semantics and culturallygrounded meanings. This paper presentsGLIMMER, a three-stage hybrid ranking systemthat evaluates how well images expressthe intended meaning of MWEs across 15 languages.Our approach uses LLM-generatedsemantic glosses as multilingual meaning anchors,combined with dual-path embeddingscoring (textual captions and visual features),and LLM-based semantic verification. Evaluatedon the ADMIRE shared task benchmark,GLIMMER achieves competitive performanceacross diverse languages without relying onparallel training data or language-specific resources.The results show that using glossesto anchor meaning helps match idioms withimages across languages and modalities, andthat combining retrieval with reasoning is morerobust than using embeddings alone.</abstract>
<identifier type="citekey">carp-2026-tiberiucarp</identifier>
<location>
<url>https://aclanthology.org/2026.mwe-1.23/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>170</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker
%A Carp, Andrei Tiberiu
%Y Ojha, Atul Kr.
%Y Mititelu, Verginica Barbu
%Y Constant, Mathieu
%Y Stoyanova, Ivelina
%Y Doğruöz, A. Seza
%Y Rademaker, Alexandre
%S Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-363-0
%F carp-2026-tiberiucarp
%X Multiword expressions (MWEs), particularlyidioms, pose persistent challengesfor vision-language systems due to theirnon-compositional semantics and culturallygrounded meanings. This paper presentsGLIMMER, a three-stage hybrid ranking systemthat evaluates how well images expressthe intended meaning of MWEs across 15 languages.Our approach uses LLM-generatedsemantic glosses as multilingual meaning anchors,combined with dual-path embeddingscoring (textual captions and visual features),and LLM-based semantic verification. Evaluatedon the ADMIRE shared task benchmark,GLIMMER achieves competitive performanceacross diverse languages without relying onparallel training data or language-specific resources.The results show that using glossesto anchor meaning helps match idioms withimages across languages and modalities, andthat combining retrieval with reasoning is morerobust than using embeddings alone.
%U https://aclanthology.org/2026.mwe-1.23/
%P 170-176
Markdown (Informal)
[tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker](https://aclanthology.org/2026.mwe-1.23/) (Carp, MWE 2026)
ACL