@inproceedings{godbersen-etal-2026-fruitcakes,
title = "Fruitcakes and Cupcakes Emerging from Noise: The {C}omposi{G}en Dataset of Compounds and Their Compositionality",
author = "Godbersen, Jule and
Kurtyigit, Sinan Cem and
Raimundo Schulz, Emma and
Rakshit, Tonmoy and
Frassinelli, Diego and
Schulte im Walde, Sabine and
Silberer, Carina",
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-1.732/",
doi = "10.63317/5irr54jotvxf",
pages = "9321--9338",
abstract = "Compounds are a complex linguistic phenomenon, as variation in their degree of compositionality often makes their interpretation non-straightforward. We consider the task of visual-linguistic compositionality prediction for English noun-noun compounds, i.e., predicting the degrees to which a compound{'}s meaning is predictable from its constituents. We introduce a new dataset, \textit{ComposiGen}, which provides constituent-specific human-elicited compositionality ratings for compounds of different concreteness categories, and includes generated visual representations for both compounds and their constituents. To enable controlled comparisons, we structure \textit{ComposiGen} such that head constituents are shared across multiple compounds (e.g., \textit{wedding cake}, \textit{cup cake}). We suggest a novel parameter-based approach leveraging constituent-to-compound image transformations to predict different degrees of visual constituent contributions to compound meaning. While our novel approach requires further exploration for validation, our overall results show that the generated images, in particular in combination with text, provide valuable information, and that simple late fusion outperforms multimodal transformers. Taken together, our findings highlight a promising avenue for future research on more efficient multimodal models for compositionality prediction. Our novel dataset offers a rich resource for future in-depth research, including the exploration of visual, constituent-based compound formation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="godbersen-etal-2026-fruitcakes">
<titleInfo>
<title>Fruitcakes and Cupcakes Emerging from Noise: The ComposiGen Dataset of Compounds and Their Compositionality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jule</namePart>
<namePart type="family">Godbersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sinan</namePart>
<namePart type="given">Cem</namePart>
<namePart type="family">Kurtyigit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Raimundo Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tonmoy</namePart>
<namePart type="family">Rakshit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Schulte im Walde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carina</namePart>
<namePart type="family">Silberer</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>Compounds are a complex linguistic phenomenon, as variation in their degree of compositionality often makes their interpretation non-straightforward. We consider the task of visual-linguistic compositionality prediction for English noun-noun compounds, i.e., predicting the degrees to which a compound’s meaning is predictable from its constituents. We introduce a new dataset, ComposiGen, which provides constituent-specific human-elicited compositionality ratings for compounds of different concreteness categories, and includes generated visual representations for both compounds and their constituents. To enable controlled comparisons, we structure ComposiGen such that head constituents are shared across multiple compounds (e.g., wedding cake, cup cake). We suggest a novel parameter-based approach leveraging constituent-to-compound image transformations to predict different degrees of visual constituent contributions to compound meaning. While our novel approach requires further exploration for validation, our overall results show that the generated images, in particular in combination with text, provide valuable information, and that simple late fusion outperforms multimodal transformers. Taken together, our findings highlight a promising avenue for future research on more efficient multimodal models for compositionality prediction. Our novel dataset offers a rich resource for future in-depth research, including the exploration of visual, constituent-based compound formation.</abstract>
<identifier type="citekey">godbersen-etal-2026-fruitcakes</identifier>
<identifier type="doi">10.63317/5irr54jotvxf</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.732/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9321</start>
<end>9338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fruitcakes and Cupcakes Emerging from Noise: The ComposiGen Dataset of Compounds and Their Compositionality
%A Godbersen, Jule
%A Kurtyigit, Sinan Cem
%A Raimundo Schulz, Emma
%A Rakshit, Tonmoy
%A Frassinelli, Diego
%A Schulte im Walde, Sabine
%A Silberer, Carina
%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 godbersen-etal-2026-fruitcakes
%X Compounds are a complex linguistic phenomenon, as variation in their degree of compositionality often makes their interpretation non-straightforward. We consider the task of visual-linguistic compositionality prediction for English noun-noun compounds, i.e., predicting the degrees to which a compound’s meaning is predictable from its constituents. We introduce a new dataset, ComposiGen, which provides constituent-specific human-elicited compositionality ratings for compounds of different concreteness categories, and includes generated visual representations for both compounds and their constituents. To enable controlled comparisons, we structure ComposiGen such that head constituents are shared across multiple compounds (e.g., wedding cake, cup cake). We suggest a novel parameter-based approach leveraging constituent-to-compound image transformations to predict different degrees of visual constituent contributions to compound meaning. While our novel approach requires further exploration for validation, our overall results show that the generated images, in particular in combination with text, provide valuable information, and that simple late fusion outperforms multimodal transformers. Taken together, our findings highlight a promising avenue for future research on more efficient multimodal models for compositionality prediction. Our novel dataset offers a rich resource for future in-depth research, including the exploration of visual, constituent-based compound formation.
%R 10.63317/5irr54jotvxf
%U https://aclanthology.org/2026.lrec-1.732/
%U https://doi.org/10.63317/5irr54jotvxf
%P 9321-9338
Markdown (Informal)
[Fruitcakes and Cupcakes Emerging from Noise: The ComposiGen Dataset of Compounds and Their Compositionality](https://aclanthology.org/2026.lrec-1.732/) (Godbersen et al., LREC 2026)
ACL