@inproceedings{bolisetty-etal-2026-moodmetric,
title = "{M}ood{M}etric at {S}em{E}val-2026 Task 4:Narrative Story Similarity and Narrative Representation Learning",
author = "Bolisetty, Samanvitha and
Ashar, Shreya and
Mittal, Nishchay and
Mishra, Pruthwik",
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-1.336/",
pages = "2664--2672",
ISBN = "979-8-89176-414-9",
abstract = "This paper presents our system for narrative similarity modeling in SemEval Task 4, focusing on transformer-based dense embedding approaches. Modeling similarity between long-form narratives is particularly challenging due to the need to capture event progression, causal structure, character dynamics, and thematic coherence beyond surface-level lexical overlap.We evaluate multiple pretrained encoder-only architectures, including DeBERTa-v3, BGE-Base, BGE-Large, and E5-Large, fine-tuned using triplet margin and contrastive objectives. In addition, we implement a hybrid lexical{--}semantic baseline combining TF-IDF and SBERT features. Our experiments analyze the impact of model scale, pooling strategies, layer freezing, training duration, and embedding-level ensembling under low-resource conditions (approximately 1,900 training triplets, with additional synthetic augmentation).Results show that larger contrastively pretrained embedding models consistently outperform smaller variants, with BGE-Large achieving the strongest standalone performance. However, performance saturates quickly, and moderate fine-tuning (4{--}5 epochs) yields optimal validation accuracy, while extended training leads to overfitting. Instruction-tuned embeddings do not demonstrate significant advantages over contrastively aligned alternatives for this task. Finally, arithmetic averaging of embeddings from diverse models produces the most robust representations, achieving approximately 65{\%} validation accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bolisetty-etal-2026-moodmetric">
<titleInfo>
<title>MoodMetric at SemEval-2026 Task 4:Narrative Story Similarity and Narrative Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samanvitha</namePart>
<namePart type="family">Bolisetty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreya</namePart>
<namePart type="family">Ashar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishchay</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</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>This paper presents our system for narrative similarity modeling in SemEval Task 4, focusing on transformer-based dense embedding approaches. Modeling similarity between long-form narratives is particularly challenging due to the need to capture event progression, causal structure, character dynamics, and thematic coherence beyond surface-level lexical overlap.We evaluate multiple pretrained encoder-only architectures, including DeBERTa-v3, BGE-Base, BGE-Large, and E5-Large, fine-tuned using triplet margin and contrastive objectives. In addition, we implement a hybrid lexical–semantic baseline combining TF-IDF and SBERT features. Our experiments analyze the impact of model scale, pooling strategies, layer freezing, training duration, and embedding-level ensembling under low-resource conditions (approximately 1,900 training triplets, with additional synthetic augmentation).Results show that larger contrastively pretrained embedding models consistently outperform smaller variants, with BGE-Large achieving the strongest standalone performance. However, performance saturates quickly, and moderate fine-tuning (4–5 epochs) yields optimal validation accuracy, while extended training leads to overfitting. Instruction-tuned embeddings do not demonstrate significant advantages over contrastively aligned alternatives for this task. Finally, arithmetic averaging of embeddings from diverse models produces the most robust representations, achieving approximately 65% validation accuracy.</abstract>
<identifier type="citekey">bolisetty-etal-2026-moodmetric</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.336/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2664</start>
<end>2672</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MoodMetric at SemEval-2026 Task 4:Narrative Story Similarity and Narrative Representation Learning
%A Bolisetty, Samanvitha
%A Ashar, Shreya
%A Mittal, Nishchay
%A Mishra, Pruthwik
%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 bolisetty-etal-2026-moodmetric
%X This paper presents our system for narrative similarity modeling in SemEval Task 4, focusing on transformer-based dense embedding approaches. Modeling similarity between long-form narratives is particularly challenging due to the need to capture event progression, causal structure, character dynamics, and thematic coherence beyond surface-level lexical overlap.We evaluate multiple pretrained encoder-only architectures, including DeBERTa-v3, BGE-Base, BGE-Large, and E5-Large, fine-tuned using triplet margin and contrastive objectives. In addition, we implement a hybrid lexical–semantic baseline combining TF-IDF and SBERT features. Our experiments analyze the impact of model scale, pooling strategies, layer freezing, training duration, and embedding-level ensembling under low-resource conditions (approximately 1,900 training triplets, with additional synthetic augmentation).Results show that larger contrastively pretrained embedding models consistently outperform smaller variants, with BGE-Large achieving the strongest standalone performance. However, performance saturates quickly, and moderate fine-tuning (4–5 epochs) yields optimal validation accuracy, while extended training leads to overfitting. Instruction-tuned embeddings do not demonstrate significant advantages over contrastively aligned alternatives for this task. Finally, arithmetic averaging of embeddings from diverse models produces the most robust representations, achieving approximately 65% validation accuracy.
%U https://aclanthology.org/2026.semeval-1.336/
%P 2664-2672
Markdown (Informal)
[MoodMetric at SemEval-2026 Task 4:Narrative Story Similarity and Narrative Representation Learning](https://aclanthology.org/2026.semeval-1.336/) (Bolisetty et al., SemEval 2026)
ACL