MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
This work addresses the challenge of adapting stance detection models to new targets and domains, which is incremental as it builds on existing few-shot learning methods.
The paper tackles the problem of stance detection across different domains and targets by proposing MLSD, a few-shot learning approach using metric learning with triplet loss, which shows statistically significant performance improvements across six models in multiple scenarios.
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.