Abstract
This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA), which predicts discrete sentiment labels, DimABSA requires predicting continuous Valence and Arousal (VA) scores on a 1-9 scale. A central challenge is that Valence and Arousal differ in prediction difficulty across languages and domains. We address this using learned homoscedastic uncertainty, where the model learns task-specific log-variance parameters to automatically balance each regression objective during training. Combined with language-specific encoders and multi-seed ensembling, LogSigma achieves 1st place on five datasets across both tracks. The learned variance weights vary substantially across languages due to differing Valence-Arousal difficulty profiles-from 0.66x for German to 2.18x for English-demonstrating that optimal task balancing is language-dependent and cannot be determined a priori.
Abstract (translated)
本文介绍LogSigma,我们为SemEval-2026任务3:维度化方面情感分析(DimABSA)所开发的系统。与传统方面情感分析(ABSA)预测离散情感标签不同,DimABSA要求预测1-9量程上的连续效价(Valence)与唤醒度(Arousal)分数。核心挑战在于效价与唤醒度在不同语言与领域中的预测难度存在差异。我们通过采用学习同方差不确定性(learned homoscedastic uncertainty)方法解决此问题,即模型在学习过程中自动调整各回归目标的任务特定对数方差参数,以实现训练时的动态平衡。结合语言特定编码器与多种子集成策略,LogSigma在双轨共计五个数据集上均取得第一名。实验显示,由于不同语言的效价-唤醒度难度谱系各异,所学方差权重在语言间存在显著差异——德语为0.66倍,英语则为2.18倍——这表明最优任务平衡具有语言依赖性,无法预先确定。
URL
https://arxiv.org/abs/2603.24896