@inproceedings{limback-stokin-etal-2026-meaning,
title = "Meaning Representations as Variational Quantum Circuits",
author = {Limb{\"a}ck-Stokin, Tilen Gaetano and
Birdavade, Tanishka A. and
Lo, Kin Ian and
Sadrzadeh, Mehrnoosh},
editor = "Zhao, Jin and
Post, Claire Benet and
Hoefer, Elizabeth",
booktitle = "Proceedings of The Seventh International Workshop on Designing Meaning Representations ({DMR} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.dmr-1.10/",
doi = "10.63317/2qyxbre9ncwk",
pages = "113--123",
abstract = "Large language and vision-language models (VLMs) struggle with a `compositionality gap'. They treat language as a sequence of tokens lacking any structure and thus rely on a large number of parameters making them computationally expensive. To address these issues, we propose CCG-VQC, a quantum framework that unifies statistical distributions with linguistic structure. Guided by Combinatory Categorial Grammar, our model maps syntactic rules into parametrised quantum circuits and models sentences as quantum states. We evaluate CCG-VQC on structural VLM benchmarks such as ARO and SVO-Swap. Our experiments show that CCG-VQC consistently outperforms a quantum bag-of-words model, as well as classical VLMs such as CLIP and OpenCLIP. CCG-VQC achieved 71.19{\%} accuracy on ARO-Attribution, significantly outperforming the parameter-matched MicroCLIP, which struggled to surpass random chance with a maximum performance of 50.85{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="limback-stokin-etal-2026-meaning">
<titleInfo>
<title>Meaning Representations as Variational Quantum Circuits</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tilen</namePart>
<namePart type="given">Gaetano</namePart>
<namePart type="family">Limbäck-Stokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanishka</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Birdavade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kin</namePart>
<namePart type="given">Ian</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrnoosh</namePart>
<namePart type="family">Sadrzadeh</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 Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="given">Benet</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Hoefer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language and vision-language models (VLMs) struggle with a ‘compositionality gap’. They treat language as a sequence of tokens lacking any structure and thus rely on a large number of parameters making them computationally expensive. To address these issues, we propose CCG-VQC, a quantum framework that unifies statistical distributions with linguistic structure. Guided by Combinatory Categorial Grammar, our model maps syntactic rules into parametrised quantum circuits and models sentences as quantum states. We evaluate CCG-VQC on structural VLM benchmarks such as ARO and SVO-Swap. Our experiments show that CCG-VQC consistently outperforms a quantum bag-of-words model, as well as classical VLMs such as CLIP and OpenCLIP. CCG-VQC achieved 71.19% accuracy on ARO-Attribution, significantly outperforming the parameter-matched MicroCLIP, which struggled to surpass random chance with a maximum performance of 50.85%.</abstract>
<identifier type="citekey">limback-stokin-etal-2026-meaning</identifier>
<identifier type="doi">10.63317/2qyxbre9ncwk</identifier>
<location>
<url>https://aclanthology.org/2026.dmr-1.10/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>113</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meaning Representations as Variational Quantum Circuits
%A Limbäck-Stokin, Tilen Gaetano
%A Birdavade, Tanishka A.
%A Lo, Kin Ian
%A Sadrzadeh, Mehrnoosh
%Y Zhao, Jin
%Y Post, Claire Benet
%Y Hoefer, Elizabeth
%S Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F limback-stokin-etal-2026-meaning
%X Large language and vision-language models (VLMs) struggle with a ‘compositionality gap’. They treat language as a sequence of tokens lacking any structure and thus rely on a large number of parameters making them computationally expensive. To address these issues, we propose CCG-VQC, a quantum framework that unifies statistical distributions with linguistic structure. Guided by Combinatory Categorial Grammar, our model maps syntactic rules into parametrised quantum circuits and models sentences as quantum states. We evaluate CCG-VQC on structural VLM benchmarks such as ARO and SVO-Swap. Our experiments show that CCG-VQC consistently outperforms a quantum bag-of-words model, as well as classical VLMs such as CLIP and OpenCLIP. CCG-VQC achieved 71.19% accuracy on ARO-Attribution, significantly outperforming the parameter-matched MicroCLIP, which struggled to surpass random chance with a maximum performance of 50.85%.
%R 10.63317/2qyxbre9ncwk
%U https://aclanthology.org/2026.dmr-1.10/
%U https://doi.org/10.63317/2qyxbre9ncwk
%P 113-123
Markdown (Informal)
[Meaning Representations as Variational Quantum Circuits](https://aclanthology.org/2026.dmr-1.10/) (Limbäck-Stokin et al., DMR 2026)
ACL
- Tilen Gaetano Limbäck-Stokin, Tanishka A. Birdavade, Kin Ian Lo, and Mehrnoosh Sadrzadeh. 2026. Meaning Representations as Variational Quantum Circuits. In Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026, pages 113–123, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).