@inproceedings{mitka-helcl-2026-cuni,
title = "{CUNI} at {S}em{E}val-2026 Task 4: Multi-Head Narrative Aspect Disentanglement via Entangled Synthetic Dataset",
author = "Mitka, Jan and
Helcl, Jindrich",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.274/",
pages = "2163--2178",
ISBN = "979-8-89176-414-9",
abstract = "We participate in Track B of the SemEval 2026 Task 4 on narrative similarity, focusing on narrative representation learning. We introduce a synthetic dataset designed to disentangle core narrative aspects-abstract theme, course of action, and outcome-and propose a multi-head multi-positive extension of the InfoNCE objective to train aspect-specific embeddings. Our best model achieves 64.25{\textbackslash}{\%} accuracy on the test set. A nearest-centroid analysis indicates partial aspect-specific structure in the submitted checkpoint, while the training dynamics reveal a partial misalignment between the contrastive objective and the triplet-based evaluation protocol."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mitka-helcl-2026-cuni">
<titleInfo>
<title>CUNI at SemEval-2026 Task 4: Multi-Head Narrative Aspect Disentanglement via Entangled Synthetic Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Mitka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindrich</namePart>
<namePart type="family">Helcl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>We participate in Track B of the SemEval 2026 Task 4 on narrative similarity, focusing on narrative representation learning. We introduce a synthetic dataset designed to disentangle core narrative aspects-abstract theme, course of action, and outcome-and propose a multi-head multi-positive extension of the InfoNCE objective to train aspect-specific embeddings. Our best model achieves 64.25\textbackslash% accuracy on the test set. A nearest-centroid analysis indicates partial aspect-specific structure in the submitted checkpoint, while the training dynamics reveal a partial misalignment between the contrastive objective and the triplet-based evaluation protocol.</abstract>
<identifier type="citekey">mitka-helcl-2026-cuni</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.274/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2163</start>
<end>2178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUNI at SemEval-2026 Task 4: Multi-Head Narrative Aspect Disentanglement via Entangled Synthetic Dataset
%A Mitka, Jan
%A Helcl, Jindrich
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F mitka-helcl-2026-cuni
%X We participate in Track B of the SemEval 2026 Task 4 on narrative similarity, focusing on narrative representation learning. We introduce a synthetic dataset designed to disentangle core narrative aspects-abstract theme, course of action, and outcome-and propose a multi-head multi-positive extension of the InfoNCE objective to train aspect-specific embeddings. Our best model achieves 64.25\textbackslash% accuracy on the test set. A nearest-centroid analysis indicates partial aspect-specific structure in the submitted checkpoint, while the training dynamics reveal a partial misalignment between the contrastive objective and the triplet-based evaluation protocol.
%U https://aclanthology.org/2026.semeval-1.274/
%P 2163-2178
Markdown (Informal)
[CUNI at SemEval-2026 Task 4: Multi-Head Narrative Aspect Disentanglement via Entangled Synthetic Dataset](https://aclanthology.org/2026.semeval-1.274/) (Mitka & Helcl, SemEval 2026)
ACL