@inproceedings{sitter-etal-2026-decomposing,
title = "Decomposing Creativity: Two Small Datasets Combining Originality Ratings and Metaphor Annotations",
author = "Sitter, Emilie and
Zarrie{\ss}, Sina and
Momen, Omar and
Herrmann, Berenike",
editor = "Egg, Markus and
Kordoni, Valia",
booktitle = "Proceedings of Learning Non-Literal Expressions with Small Data @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nonliteral-1.11/",
doi = "10.63317/486rgpcgguib",
pages = "119--132",
abstract = "We introduce MetaphOrig, a small dataset comprising two genre-specific collections of spatial descriptions for the study of linguistic creativity and Non-Literal Expressions (NLEs). The sentence-level spatial descriptions were extracted from two distinct genre- and time-specific source corpora. Both source corpora comprise German texts: literary prose from the 18th to 20th century (KOLIMO) and factual travel reports from the 21st century (Wikivoyage). Along with the spatial descriptions, the dataset contains sentence-level originality ratings obtained through crowdsourcing and from four different LLMs (GPT-5, Qwen2.5-32B-Instruct, Mistral-Small-3.2-24B-Instruct, and Llama-3.2-3B), and word-level metaphor annotations. We provide the MetaphOrig datasets, including all annotations, to the community. The subsets can be used for further research on linguistic creativity or metaphor, either in one specific textual domain or comparatively across the two domains. We conduct an illustrative study on the dataset, treating originality as a proxy of textual creativity. In both subsets, we investigate potential correlations between sentence-level originality ratings and the density of metaphorical expressions within each sentence. We find the correlation to be present only in the KOLIMO subset. A comparison of human and LLM originality ratings shows that this pattern holds for both types of ratings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sitter-etal-2026-decomposing">
<titleInfo>
<title>Decomposing Creativity: Two Small Datasets Combining Originality Ratings and Metaphor Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emilie</namePart>
<namePart type="family">Sitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Momen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berenike</namePart>
<namePart type="family">Herrmann</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 Learning Non-Literal Expressions with Small Data @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Egg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valia</namePart>
<namePart type="family">Kordoni</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>We introduce MetaphOrig, a small dataset comprising two genre-specific collections of spatial descriptions for the study of linguistic creativity and Non-Literal Expressions (NLEs). The sentence-level spatial descriptions were extracted from two distinct genre- and time-specific source corpora. Both source corpora comprise German texts: literary prose from the 18th to 20th century (KOLIMO) and factual travel reports from the 21st century (Wikivoyage). Along with the spatial descriptions, the dataset contains sentence-level originality ratings obtained through crowdsourcing and from four different LLMs (GPT-5, Qwen2.5-32B-Instruct, Mistral-Small-3.2-24B-Instruct, and Llama-3.2-3B), and word-level metaphor annotations. We provide the MetaphOrig datasets, including all annotations, to the community. The subsets can be used for further research on linguistic creativity or metaphor, either in one specific textual domain or comparatively across the two domains. We conduct an illustrative study on the dataset, treating originality as a proxy of textual creativity. In both subsets, we investigate potential correlations between sentence-level originality ratings and the density of metaphorical expressions within each sentence. We find the correlation to be present only in the KOLIMO subset. A comparison of human and LLM originality ratings shows that this pattern holds for both types of ratings.</abstract>
<identifier type="citekey">sitter-etal-2026-decomposing</identifier>
<identifier type="doi">10.63317/486rgpcgguib</identifier>
<location>
<url>https://aclanthology.org/2026.nonliteral-1.11/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>119</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decomposing Creativity: Two Small Datasets Combining Originality Ratings and Metaphor Annotations
%A Sitter, Emilie
%A Zarrieß, Sina
%A Momen, Omar
%A Herrmann, Berenike
%Y Egg, Markus
%Y Kordoni, Valia
%S Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F sitter-etal-2026-decomposing
%X We introduce MetaphOrig, a small dataset comprising two genre-specific collections of spatial descriptions for the study of linguistic creativity and Non-Literal Expressions (NLEs). The sentence-level spatial descriptions were extracted from two distinct genre- and time-specific source corpora. Both source corpora comprise German texts: literary prose from the 18th to 20th century (KOLIMO) and factual travel reports from the 21st century (Wikivoyage). Along with the spatial descriptions, the dataset contains sentence-level originality ratings obtained through crowdsourcing and from four different LLMs (GPT-5, Qwen2.5-32B-Instruct, Mistral-Small-3.2-24B-Instruct, and Llama-3.2-3B), and word-level metaphor annotations. We provide the MetaphOrig datasets, including all annotations, to the community. The subsets can be used for further research on linguistic creativity or metaphor, either in one specific textual domain or comparatively across the two domains. We conduct an illustrative study on the dataset, treating originality as a proxy of textual creativity. In both subsets, we investigate potential correlations between sentence-level originality ratings and the density of metaphorical expressions within each sentence. We find the correlation to be present only in the KOLIMO subset. A comparison of human and LLM originality ratings shows that this pattern holds for both types of ratings.
%R 10.63317/486rgpcgguib
%U https://aclanthology.org/2026.nonliteral-1.11/
%U https://doi.org/10.63317/486rgpcgguib
%P 119-132
Markdown (Informal)
[Decomposing Creativity: Two Small Datasets Combining Originality Ratings and Metaphor Annotations](https://aclanthology.org/2026.nonliteral-1.11/) (Sitter et al., NonLiteral 2026)
ACL