ttda704 at SemEval-2026 Task 4: Modeling Narrative Structures via Pseudonymization and Multi-View Sentence Alignment
Not on the map. Why?
Abstract (arXiv)
We present our approach to SemEval 2026 Task 4: Narrative Story Similarity and Narrative Representation Learning. Our solution uses contrastive learning with fine-tuned sentence transformers to capture narrative similarity across abstract themes, course of action, and outcomes. We develop two pipelines: (Track A) a single-view method that encodes full narratives with smart layer freezing to reduce overfitting, and (Track B) a multi-view method that models theme, plot, and outcome with view-specific projection heads and self-supervised alignment. Both pipelines build on sentence-transformers models and are trained with contrastive loss on synthetic data. The code is available at the following GitHub repository: https://github.com/dinhthienan33/SemEval2026-Task4-ttda704.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 23 references that are in the map. First posted on arXiv 14 Jun 2026.
Builds on
8 of 23 references.
References · 8
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
- 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
- 2020A Survey on Contrastive Self-supervised Learningcited by 554
- 2024Are Large Language Models Capable of Generating Human-Level Narratives?cited by 79
- 2022Multi-View Document Representation Learning for Open-Domain Dense Retrievalcited by 41
- 2023Improving Contrastive Learning of Sentence Embeddings from AI Feedbackcited by 29
- 2024Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMscited by 28
Built on by
Not cited yet.