ttda704 at SemEval-2026 Task 4: Modeling Narrative Structures via Pseudonymization and Multi-View Sentence Alignment
Year: 2026
Type: conference-paper
Abstract: 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 viewspecific projection heads and self-supervised alignment.Both pipelines build on sentencetransformers models and are trained with contrastive loss on synthetic data.
Authors: Tai Tran Tan, An Thien
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166830163