Guardado en:
Detalles Bibliográficos
Autores principales: Gera, Parush, Neal, Tempestt
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.03725
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916931999629312
author Gera, Parush
Neal, Tempestt
author_facet Gera, Parush
Neal, Tempestt
contents We present the novel approach for stance detection across domains and targets, Metric Learning-Based Few-Shot Learning for Cross-Target and Cross-Domain Stance Detection (MLSD). MLSD utilizes metric learning with triplet loss to capture semantic similarities and differences between stance targets, enhancing domain adaptation. By constructing a discriminative embedding space, MLSD allows a cross-target or cross-domain stance detection model to acquire useful examples from new target domains. We evaluate MLSD in multiple cross-target and cross-domain scenarios across two datasets, showing statistically significant improvement in stance detection performance across six widely used stance detection models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03725
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
Gera, Parush
Neal, Tempestt
Computation and Language
Artificial Intelligence
Machine Learning
We present the novel approach for stance detection across domains and targets, Metric Learning-Based Few-Shot Learning for Cross-Target and Cross-Domain Stance Detection (MLSD). MLSD utilizes metric learning with triplet loss to capture semantic similarities and differences between stance targets, enhancing domain adaptation. By constructing a discriminative embedding space, MLSD allows a cross-target or cross-domain stance detection model to acquire useful examples from new target domains. We evaluate MLSD in multiple cross-target and cross-domain scenarios across two datasets, showing statistically significant improvement in stance detection performance across six widely used stance detection models.
title MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.03725