Citation
Downloads
Abstract
We describe our submission to SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning.The task requires (i) selecting, for a given anchor story summary, which of two candidate summaries is narratively closer (Track A) and (ii) producing a narrative representation of a story as a vector embedding (Track B).Our approach emphasizes interpretability by explicitly eliciting three narrativity aspects with a prompted large language model.We then construct a fixed-size narrative embedding by concatenating aspect-wise representations, comparing a static-embedding baseline (GloVe) to contextualized sentence-transformer embeddings (all-MiniLM-L6-v2).On the development set, the sentence-transformer variant outperforms the static baseline and achieves 61.5% accuracy on Track A, while the GloVe variant performs near chance.Our official submission reaches 60.25% accuracy on the Track A test set and 57.75% accuracy on Track B.Additional ablations show that the aspect pipeline slightly outperforms raw-text embeddings, but that aspect contributions are uneven.Qualitative analysis suggests that failures often stem from inconsistent aspect generation and from overemphasizing theme overlap over event-level similarity.
BibTeX
@inproceedings{pagel2026a,
author = {Janis Pagel and Nils Reiter},
booktitle = {{Proceedings of the 20th International Workshop on Semantic Evaluation (2026)}},
doi = {10.18653/v1/2026.semeval-1.299},
location = {San Diego, CA, USA},
month = {7},
pages = {2376--2383},
title = {{Spinfo Cologne at SemEval-2026 Task 4: Explainable Creation of Narrativity Embeddings}},
year = {2026},
}
RIS
TY - CPAPER TI - Spinfo Cologne at SemEval-2026 Task 4: Explainable Creation of Narrativity Embeddings AU - Janis Pagel AU - Nils Reiter PY - 2026 J2 - Proceedings of the 20th International Workshop on Semantic Evaluation (2026) DO - 10.18653/v1/2026.semeval-1.299 CY - San Diego, CA, USA SP - 2376 EP - 2383 ER -